Abstract: Speech technology and systems in human computer interaction have witnessed a stable and remarkable advancement over the last two decades. Today, speech technologies are commercially available for an unlimited but interesting range of tasks. These technologies enable machines to respond correctly and reliably to human voices, and provide useful and valuable services. This thesis presents the characteristics of emotion in voice and on that basis propose a new method to detecting emotion in a simplified way by using a prosodic features and spectral from speech. We classify seven emotions: happy, anger, fear, disgust, sadness and neutral inner state. This thesis discusses the method to extract features from a recorded speech sample, and using those features, to detect the emotion of the subject. Every emotion comprises different vocal parameters exhibiting diverse characteristics of speech, which is used for preliminary classification. Then Mel-Frequency Cepstrum Coefficient (MFCC) method was used to extract spectral features. The MFCC coefficients were again trained by Artificial Neural Network (ANN) which then classifies the input in particular emotional class.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Study: Creating Buzz: The Neural Correlates of Effective Message PropagationDaniel Honigman
The document discusses a study that examined the neural correlates of effective message propagation. Specifically:
- Participants ("interns") viewed descriptions of TV show ideas in an fMRI scanner and rated their willingness to recommend each idea.
- Interns later discussed each idea on video, which were shown to other participants ("producers") who rated their willingness to further spread each idea.
- Ideas that were more successfully spread to producers exhibited greater neural activity in the interns' mentalizing and reward systems during initial viewing, suggesting these systems enable effective influence.
- Individual differences in ability to influence others' ratings were linked to greater mentalizing activity, supporting its role in predicting others' interests.
BASIC ANALYSIS ON PROSODIC FEATURES IN EMOTIONAL SPEECHIJCSEA Journal
Speech is a rich source of information which gives not only about what a speaker says, but also about what the speaker’s attitude is toward the listener and toward the topic under discussion—as well as the speaker’s own current state of mind. Recently increasing attention has been directed to the study of the emotional content of speech signals, and hence, many systems have been proposed to identify the emotional content of a spoken utterance. The focus of this research work is to enhance man machine interface by focusing on user’s speech emotion. This paper gives the results of the basic analysis on prosodic features and also compares the prosodic features
of, various types and degrees of emotional expressions in Tamil speech based on the auditory impressions between the two genders of speakers as well as listeners. The speech samples consist of “neutral” speech as well as speech with three types of emotions (“anger”, “joy”, and “sadness”) of three degrees (“light”, “medium”, and “strong”). A listening test is also being conducted using 300 speech samples uttered by students at the ages of 19 -22 the ages of 19-22 years old. The features of prosodic parameters based on the emotional speech classified according to the auditory impressions of the subjects are analyzed. Analysis results suggest that prosodic features that identify their emotions and degrees are not only speakers’ gender dependent, but also listeners’ gender dependent.
A MODEL BASED ON SENTIMENTS ANALYSIS FOR STOCK EXCHANGE PREDICTION - CASE STU...csandit
Predicting the behavior of shares in the stock market is a complex problem, that involves variables not always known and can undergo various influences, from the collective emotion to high-profile news. Such volatility, can represent considerable financial losses for investors. In order to anticipate such changes in the market, it has been proposed various mechanisms to try to predict the behavior of an asset in the stock market, based on previously existing information.
Such mechanisms include statistical data only, without considering the collective feeling. This article, is going to use natural language processing algorithms (LPN) to determine the collective mood on assets and later with the help of the SVM algorithm to extract patterns in an attempt to predict the active behavior. Nevertheless it is important to note that such approach is not intended to be the main factor in the decision making process, but rather an aid tool, which combined with other information, can provide higher accuracy for the solution of this problem
This document summarizes research on the use of emoticons in computer-mediated communication (CMC) and their impact on interactivity. It outlines the history of CMC and reviews literature showing that emoticons are used to communicate more concisely and express emotions. Studies discussed found that perceived playfulness driven by text and emoticon use facilitates social relationships on messaging platforms. The research questions posed examine the motives for and emotional value of emoticon use, and how emoticons influence interactivity and are used on social media. The conclusion notes limitations in understanding emoticon usage but the potential for further research as CMC continues developing.
Sentiment Analysis on Twitter Dataset using R Languageijtsrd
Sentiment Analysis involves determining the evaluative nature of a piece of text. A product review can express a positive, negative, or neutral sentiment or polarity . Automatically identifying sentiment expressed in text has a number of applications, including tracking sentiment towards Movie reviews and Automobile reviews improving customer relation models, detecting happiness and well being, and improving automatic dialogue systems. The evaluative intensity for both positive and negative terms changes in a negated context, and the amount of change varies from term to term. To adequately capture the impact of negation on individual terms, here proposed to empirically estimate the sentiment scores of terms in negated context from movie review and auto mobile review, and built two lexicons, one for terms in negated contexts and one for terms in affirmative non negated contexts. By using these Affirmative Context Lexicons and Negated Context Lexicons were able to significantly improve the performance of the overall sentiment analysis system on both tasks. This thesis have proposed a sentiment analysis system that detects the sentiment of corpus dataset using movie review and Automobile review as well as the sentiment of a term a word or a phrase within a message term level task using R language. B. Nagajothi | Dr. R. Jemima Priyadarsini "Sentiment Analysis on Twitter Dataset using R Language" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-6 , October 2019, URL: https://www.ijtsrd.com/papers/ijtsrd28071.pdf Paper URL: https://www.ijtsrd.com/computer-science/data-miining/28071/sentiment-analysis-on-twitter-dataset-using-r-language/b-nagajothi
Review on Opinion Mining for Fully Fledged Systemijeei-iaes
Humans communication is generally under the control of emotions and full of opinions. Emotions an d their opinions plays an important role in thinking process of mind, influences the human actions too. Sentiment analysis is one of the ways to explore user’s opinion made on any social media and networking site for various commercial applications in number of fields. This paper takes into account the basis requirements of opinion mining to explore the present techniques used to develop a fully fledged system. Is highlights the opportunities or deployment and research of such systems. The available tools used for building such applications have even presented with their merits and limitations.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Study: Creating Buzz: The Neural Correlates of Effective Message PropagationDaniel Honigman
The document discusses a study that examined the neural correlates of effective message propagation. Specifically:
- Participants ("interns") viewed descriptions of TV show ideas in an fMRI scanner and rated their willingness to recommend each idea.
- Interns later discussed each idea on video, which were shown to other participants ("producers") who rated their willingness to further spread each idea.
- Ideas that were more successfully spread to producers exhibited greater neural activity in the interns' mentalizing and reward systems during initial viewing, suggesting these systems enable effective influence.
- Individual differences in ability to influence others' ratings were linked to greater mentalizing activity, supporting its role in predicting others' interests.
BASIC ANALYSIS ON PROSODIC FEATURES IN EMOTIONAL SPEECHIJCSEA Journal
Speech is a rich source of information which gives not only about what a speaker says, but also about what the speaker’s attitude is toward the listener and toward the topic under discussion—as well as the speaker’s own current state of mind. Recently increasing attention has been directed to the study of the emotional content of speech signals, and hence, many systems have been proposed to identify the emotional content of a spoken utterance. The focus of this research work is to enhance man machine interface by focusing on user’s speech emotion. This paper gives the results of the basic analysis on prosodic features and also compares the prosodic features
of, various types and degrees of emotional expressions in Tamil speech based on the auditory impressions between the two genders of speakers as well as listeners. The speech samples consist of “neutral” speech as well as speech with three types of emotions (“anger”, “joy”, and “sadness”) of three degrees (“light”, “medium”, and “strong”). A listening test is also being conducted using 300 speech samples uttered by students at the ages of 19 -22 the ages of 19-22 years old. The features of prosodic parameters based on the emotional speech classified according to the auditory impressions of the subjects are analyzed. Analysis results suggest that prosodic features that identify their emotions and degrees are not only speakers’ gender dependent, but also listeners’ gender dependent.
A MODEL BASED ON SENTIMENTS ANALYSIS FOR STOCK EXCHANGE PREDICTION - CASE STU...csandit
Predicting the behavior of shares in the stock market is a complex problem, that involves variables not always known and can undergo various influences, from the collective emotion to high-profile news. Such volatility, can represent considerable financial losses for investors. In order to anticipate such changes in the market, it has been proposed various mechanisms to try to predict the behavior of an asset in the stock market, based on previously existing information.
Such mechanisms include statistical data only, without considering the collective feeling. This article, is going to use natural language processing algorithms (LPN) to determine the collective mood on assets and later with the help of the SVM algorithm to extract patterns in an attempt to predict the active behavior. Nevertheless it is important to note that such approach is not intended to be the main factor in the decision making process, but rather an aid tool, which combined with other information, can provide higher accuracy for the solution of this problem
This document summarizes research on the use of emoticons in computer-mediated communication (CMC) and their impact on interactivity. It outlines the history of CMC and reviews literature showing that emoticons are used to communicate more concisely and express emotions. Studies discussed found that perceived playfulness driven by text and emoticon use facilitates social relationships on messaging platforms. The research questions posed examine the motives for and emotional value of emoticon use, and how emoticons influence interactivity and are used on social media. The conclusion notes limitations in understanding emoticon usage but the potential for further research as CMC continues developing.
Sentiment Analysis on Twitter Dataset using R Languageijtsrd
Sentiment Analysis involves determining the evaluative nature of a piece of text. A product review can express a positive, negative, or neutral sentiment or polarity . Automatically identifying sentiment expressed in text has a number of applications, including tracking sentiment towards Movie reviews and Automobile reviews improving customer relation models, detecting happiness and well being, and improving automatic dialogue systems. The evaluative intensity for both positive and negative terms changes in a negated context, and the amount of change varies from term to term. To adequately capture the impact of negation on individual terms, here proposed to empirically estimate the sentiment scores of terms in negated context from movie review and auto mobile review, and built two lexicons, one for terms in negated contexts and one for terms in affirmative non negated contexts. By using these Affirmative Context Lexicons and Negated Context Lexicons were able to significantly improve the performance of the overall sentiment analysis system on both tasks. This thesis have proposed a sentiment analysis system that detects the sentiment of corpus dataset using movie review and Automobile review as well as the sentiment of a term a word or a phrase within a message term level task using R language. B. Nagajothi | Dr. R. Jemima Priyadarsini "Sentiment Analysis on Twitter Dataset using R Language" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-6 , October 2019, URL: https://www.ijtsrd.com/papers/ijtsrd28071.pdf Paper URL: https://www.ijtsrd.com/computer-science/data-miining/28071/sentiment-analysis-on-twitter-dataset-using-r-language/b-nagajothi
Review on Opinion Mining for Fully Fledged Systemijeei-iaes
Humans communication is generally under the control of emotions and full of opinions. Emotions an d their opinions plays an important role in thinking process of mind, influences the human actions too. Sentiment analysis is one of the ways to explore user’s opinion made on any social media and networking site for various commercial applications in number of fields. This paper takes into account the basis requirements of opinion mining to explore the present techniques used to develop a fully fledged system. Is highlights the opportunities or deployment and research of such systems. The available tools used for building such applications have even presented with their merits and limitations.
Abstract: This Project describes a visual sensor system used in the field of robotics for identification and tracking of the colored object. The program is designed to capture an Object through a Camera. It describes image capturing and processing techniques, followed by an introduction to actual robotic application to trace the Object using the serial COM port of the PC. The whole system of making a robot to follow an object can be divided into four blocks: image acquisition, processing of image, decision-making and motion control.
Abstract: A quality of service framework is a fundamental component of a 4G broadband wireless network for satisfactory service delivery of evolving Internet applications to end users, and managing the network resources. Today’s popular mobile Internet applications, such as voice, gaming, streaming, and social networking services, have diverse traffic characteristics and, consequently, different QoS requirements. A rather flexible QoS framework is highly desirable to be future-proof to deliver the incumbent as well as emerging mobile Internet applications. This article highlights QoS frameworks and features of OFDMA-based 4G technologies — IEEE 802.16e, IEEE 802.16m — to support various applications’ QoS requirements. A few advanced QoS features such as new scheduling service (i.e., aGP), quick access, delayed bandwidth request, and priority controlled access in IEEE 802.16m are explained in detail. A brief comparison of the QoS framework of the aforementioned technologies is also provide
Abstract: The main communication methods used by deaf people are sign language, but opposed to common thought, there is no specific universal sign language: every country or even regional group uses its own set of signs. The use of sign language in digital systems can enhance communication in both directions: animated avatars can synthesize signals based on voice or text recognition; and sign language can be translated into various text or sound forms based on different images, videos and sensors input. The ultimate goal of this research, but it is not a simple spelling of spoken language, so that recognizing different signs or letters of the alphabet (which has been a common approach) is not sufficient for its transcription and automatic interpretation. Here proposes an algorithm and method for an application this would help us in recognising the various user defined signs. The palm images of right and left hand are loaded at runtime. Firstly these images will be seized and stored in directory. Then technique called Template matching is used for finding areas of an image that match (are similar) to a template image (patch). Our goal is to detect the highest matching area. We need two primary components- A) Source image (I): In the template image in which we try to find a match. B) Template image (T): The patch image which will be compared to the template image. In proposed system user defined patterns will be having 60% accuracy while default patterns will be provided with 80% accuracy.
Effects of Carriers on the Transmission dynamics of Non- Typhoidal Salmonella...paperpublications3
Abstract:The impact of control strategies to effectively control the burden of the effect of carriers on the salmonella diarrhea is investigated in this paper. This model studies the dynamics of diarrhea by formulating and analyzing the impact of carriers. According to the pathogenesis of salmonella, the model had been designed as an SIR system comprising of a non-constant population. The disease-free state and basic reproduction number (R0) have been computed for this system. In epidemics, there are always two cases: R0<1>1 (epidemic existing state).
Robust Image Watermarking Based on Dual Intermediate Significant Bit (DISB) I...paperpublications3
Abstract: The most important requirements should be available on any watermarking systems which are the robustness against possible attacks and the quality of the watermarked images. In most applications, the watermarking algorithm embeds the watermark have to be robust against possible attacks and keep the quality of the host media as possible. The relationship between the two requirements is completely conflict. In this study, the method focuses on the robustness against RST attacks for the watermarked image based on Dual Intermediate Significant Bit (DISB) model. This method requires embedding two bits into every pixel of the original image, while and the other six bits are changed so as to directly assimilate the original pixel. In the case, when the two hidden bits are equal or not equal to the original bits, there is a need to use mathematical equations to solve this problem which derived and applied in this study. The results show that the proposed model also produces robustness watermarked images after applying geometric attacks on the RGB images as compared to our previous grayscale images. The best values investigated when the Peak Signal to Noise Ratio (PSNR) is equal or more than 30db, and finding the best Normalized Cross Correlation (NCC) to evaluate the image resistance against attacks. The best values investigated for Rotation when the two embedded bits are k1=1 and k2=4, for Scaling when the two embedded bits are k1=2 and k2=4 , for Translation when the two embedded bits are k1=3 and k2=4.
Analysis of occurrence of digit 0 in first 10 billion digits of π after decim...paperpublications3
Abstract: π has fascinated mathematicians from ancient era. In fact, every irrational number has that potential owing to the non-recursive pattern of infinite non-zero digits after the decimal point and their random occurrence. The present work is another attempt to unveil this mystery by analyzing the occurrence of digit 0 in first 10 billion digits of π after Decimal Point in Decimal Representation. Both successive and non-successive occurrences of 0 in π have been extensively analyzed.
Linked List Implementation of Discount Pricing in Cloudpaperpublications3
The document discusses implementing a linked list approach to optimize resource scheduling and pricing in cloud computing environments. It proposes a Randomized Online Stack-centric Scheduling Algorithm (ROSA) using a doubly linked list to maintain resource status and allocate resources flexibly without strict time constraints. This allows multiple customers to share resources and enjoy volume discounts without needing to adjust time limits. The approach aims to maximize resource utilization while minimizing customer costs through broker-mediated scheduling of customer requests among cloud providers.
Abstract: As profound web developer at quick pace, there has been expanded enthusiasm for method that assists proficiently with finding profound web interfaces. Nonetheless, because of the extensive volume of web assets and the dynamic way of profound web, accomplishing wide scope and high productivity is a testing issue. We propose a two-stage structure, in particular Smart Crawler, for effective gathering profound web interfaces. In the first stage, Smart Crawler performs site-based hunting down focus pages with the assistance of web indexes, abstaining from going by countless. To accomplish more exact results for an engaged slither, Smart Crawler positions sites to organize profoundly pertinent ones for a given point. In the second stage, Smart Crawler accomplishes quick in-site excavating so as to see most significant connections with a versatile connection positioning. To dispense with inclination on going by some exceedingly significant connections in shrouded web indexes, we outline a connection tree information structure to accomplish more extensive scope for a site. Our test results on an arrangement of delegate areas demonstrate the readiness and precision of our proposed crawler structure, which effectively recovers profound web interfaces from huge scale destinations and accomplishes higher harvest rates than different crawlers.
Applications of Artificial Neural Network in Forecasting of Stock Market Indexpaperpublications3
Abstract: Prediction in any field is a challenging and unnerving process. Stock market is a promising financial investment that can generate great wealth. However, under the impact of Globalization Stock Market Prediction (SMP) accuracy has become more challenging and rewarding for the researchers and participants in the stock market. Artificial Neural Networks (ANN) have been found to be an efficient tool in modeling stock prices and quite a large number of studies have been done on it. ANN modeling of stock prices of selected stocks under NSE is attempted to predict the next day’s price. The network developed consists of one input layer, hidden layer and output layer with four, nine and one nodes respectively. The input being the closing price of the previous four days and output being the price for the next day. In the first section the adaptability of neural networks in stock market prediction is discussed, in the second section we discuss the traditional methods that were being used earlier for stock market prediction, in the third section we discuss the justification for using neural networks and how it is better over traditional methods, in the fourth section we discuss the basics of neural networks, section five gives an overview of data and methodology being used, in section six we have discussed the various forecasting errors methods to calculate the error, in section seven we have presented our results. The aim of this paper is to provide an overview of the application of artificial neural network in stock market prediction.
Command Transfer Protocol (CTP) for Distributed or Parallel Computationpaperpublications3
Abstract: In this paper, an improved version of a new networking protocol CTP for distributed or parallel computations is presented. In common, it is suitable just for fast, reliable and feature full interchange of small messages. CTP is a transport level API which helps in incrementing the speed of interchange. CTP is designed to allow general configurability, enabling its use in a wide range of general purpose and specialized applications. CTP covers a number of layers, from transport layer to application layer, proves that the area of its responsibility starts from relatively low level and goes to a high one.
Pobreza, condição de nascença, desgraça, destinoLucas Castro
A empresa de tecnologia anunciou um novo smartphone com câmera aprimorada, processador mais rápido e bateria de maior duração. O dispositivo também possui tela maior e armazenamento expansível, com preço sugerido a partir de $599. Analistas esperam que o aparelho ajude a empresa a aumentar sua participação no competitivo mercado de smartphones.
The document discusses the benefits of exercise for mental health. Regular physical activity can help reduce anxiety and depression and improve mood and cognitive function. Exercise causes chemical changes in the brain that may help protect against developing mental illness and improve symptoms for those who already suffer from conditions like anxiety and depression.
The document discusses the unlikelihood of OPEC's proposed oil freeze plan taking effect by the end of 2016. It notes that while OPEC members agreed in September to potentially curb oil production, there are several indications this plan will not be implemented. Key factors include inconsistencies between meetings, reluctance of some countries to participate, and the lack of agreed upon production quotas. Given OPEC's poor track record with past agreements and uncertain market and demand conditions, most analysts believe a binding deal in 2016 is unlikely and actual reductions may not occur until 2017 if at all.
Este documento presenta 5 ejercicios de fórmulas en Excel. El primero muestra una fórmula para verificar si un número en la celda A1 es mayor o menor que 100. El segundo calcula el IVA de un subtotal en la celda A5, siempre que sea mayor a 10, de lo contrario muestra un mensaje. El tercero identifica si un número en A5 es par o impar. El cuarto indica si un dato en A5 corresponde a un usuario mayor o menor de edad.
O documento descreve a evolução do sistema operacional Android da Google, mencionando as versões KitKat 4.4, Jelly Bean 4.1 e 4.3, e descrevendo brevemente os recursos básicos do Android, como acesso a aplicativos de entretenimento, mapas, armazenamento e e-mail.
Literature Review On: ”Speech Emotion Recognition Using Deep Neural Network”IRJET Journal
The document discusses speech emotion recognition using deep neural networks. It first provides an overview of SER and the challenges in the field. It then reviews 20 research papers on the topic, finding that most use deep neural network techniques like CNNs and DNNs for model building. The papers evaluated various datasets and algorithms, with accuracy ranging from 84% to 90%. Overall limitations identified included the need for more data, handling of multiple simultaneous emotions, and improving cross-corpus performance. The literature review contributes to knowledge in using machine learning for SER.
Signal Processing Tool for Emotion Recognitionidescitation
In the course of realization of modern day robots,
which not only perform tasks, but also behaves like human
beings during their interaction with the natural environment,
it is essential for us to impart knowledge of the underlying
emotions in the spoken utterances of human beings to the
robots, enabling them to be consistent, whole, complete and
perfect. To this end, it is essential for them too to understand
and identify the human emotions. For this reason, stress is
laid now-a-days on the study of emotional content of the speech
and accordingly speech emotion recognition engines have been
proposed. This paper is a survey of the main aspects of speech
emotion recognition, namely, features extractions and types
of features commonly used, selection of most informed
features from the original dataset of the features, and
classification of the features according to different classifying
techniques based on relative information regarding commonly
used database for the speech emotion recognition.
Abstract: This Project describes a visual sensor system used in the field of robotics for identification and tracking of the colored object. The program is designed to capture an Object through a Camera. It describes image capturing and processing techniques, followed by an introduction to actual robotic application to trace the Object using the serial COM port of the PC. The whole system of making a robot to follow an object can be divided into four blocks: image acquisition, processing of image, decision-making and motion control.
Abstract: A quality of service framework is a fundamental component of a 4G broadband wireless network for satisfactory service delivery of evolving Internet applications to end users, and managing the network resources. Today’s popular mobile Internet applications, such as voice, gaming, streaming, and social networking services, have diverse traffic characteristics and, consequently, different QoS requirements. A rather flexible QoS framework is highly desirable to be future-proof to deliver the incumbent as well as emerging mobile Internet applications. This article highlights QoS frameworks and features of OFDMA-based 4G technologies — IEEE 802.16e, IEEE 802.16m — to support various applications’ QoS requirements. A few advanced QoS features such as new scheduling service (i.e., aGP), quick access, delayed bandwidth request, and priority controlled access in IEEE 802.16m are explained in detail. A brief comparison of the QoS framework of the aforementioned technologies is also provide
Abstract: The main communication methods used by deaf people are sign language, but opposed to common thought, there is no specific universal sign language: every country or even regional group uses its own set of signs. The use of sign language in digital systems can enhance communication in both directions: animated avatars can synthesize signals based on voice or text recognition; and sign language can be translated into various text or sound forms based on different images, videos and sensors input. The ultimate goal of this research, but it is not a simple spelling of spoken language, so that recognizing different signs or letters of the alphabet (which has been a common approach) is not sufficient for its transcription and automatic interpretation. Here proposes an algorithm and method for an application this would help us in recognising the various user defined signs. The palm images of right and left hand are loaded at runtime. Firstly these images will be seized and stored in directory. Then technique called Template matching is used for finding areas of an image that match (are similar) to a template image (patch). Our goal is to detect the highest matching area. We need two primary components- A) Source image (I): In the template image in which we try to find a match. B) Template image (T): The patch image which will be compared to the template image. In proposed system user defined patterns will be having 60% accuracy while default patterns will be provided with 80% accuracy.
Effects of Carriers on the Transmission dynamics of Non- Typhoidal Salmonella...paperpublications3
Abstract:The impact of control strategies to effectively control the burden of the effect of carriers on the salmonella diarrhea is investigated in this paper. This model studies the dynamics of diarrhea by formulating and analyzing the impact of carriers. According to the pathogenesis of salmonella, the model had been designed as an SIR system comprising of a non-constant population. The disease-free state and basic reproduction number (R0) have been computed for this system. In epidemics, there are always two cases: R0<1>1 (epidemic existing state).
Robust Image Watermarking Based on Dual Intermediate Significant Bit (DISB) I...paperpublications3
Abstract: The most important requirements should be available on any watermarking systems which are the robustness against possible attacks and the quality of the watermarked images. In most applications, the watermarking algorithm embeds the watermark have to be robust against possible attacks and keep the quality of the host media as possible. The relationship between the two requirements is completely conflict. In this study, the method focuses on the robustness against RST attacks for the watermarked image based on Dual Intermediate Significant Bit (DISB) model. This method requires embedding two bits into every pixel of the original image, while and the other six bits are changed so as to directly assimilate the original pixel. In the case, when the two hidden bits are equal or not equal to the original bits, there is a need to use mathematical equations to solve this problem which derived and applied in this study. The results show that the proposed model also produces robustness watermarked images after applying geometric attacks on the RGB images as compared to our previous grayscale images. The best values investigated when the Peak Signal to Noise Ratio (PSNR) is equal or more than 30db, and finding the best Normalized Cross Correlation (NCC) to evaluate the image resistance against attacks. The best values investigated for Rotation when the two embedded bits are k1=1 and k2=4, for Scaling when the two embedded bits are k1=2 and k2=4 , for Translation when the two embedded bits are k1=3 and k2=4.
Analysis of occurrence of digit 0 in first 10 billion digits of π after decim...paperpublications3
Abstract: π has fascinated mathematicians from ancient era. In fact, every irrational number has that potential owing to the non-recursive pattern of infinite non-zero digits after the decimal point and their random occurrence. The present work is another attempt to unveil this mystery by analyzing the occurrence of digit 0 in first 10 billion digits of π after Decimal Point in Decimal Representation. Both successive and non-successive occurrences of 0 in π have been extensively analyzed.
Linked List Implementation of Discount Pricing in Cloudpaperpublications3
The document discusses implementing a linked list approach to optimize resource scheduling and pricing in cloud computing environments. It proposes a Randomized Online Stack-centric Scheduling Algorithm (ROSA) using a doubly linked list to maintain resource status and allocate resources flexibly without strict time constraints. This allows multiple customers to share resources and enjoy volume discounts without needing to adjust time limits. The approach aims to maximize resource utilization while minimizing customer costs through broker-mediated scheduling of customer requests among cloud providers.
Abstract: As profound web developer at quick pace, there has been expanded enthusiasm for method that assists proficiently with finding profound web interfaces. Nonetheless, because of the extensive volume of web assets and the dynamic way of profound web, accomplishing wide scope and high productivity is a testing issue. We propose a two-stage structure, in particular Smart Crawler, for effective gathering profound web interfaces. In the first stage, Smart Crawler performs site-based hunting down focus pages with the assistance of web indexes, abstaining from going by countless. To accomplish more exact results for an engaged slither, Smart Crawler positions sites to organize profoundly pertinent ones for a given point. In the second stage, Smart Crawler accomplishes quick in-site excavating so as to see most significant connections with a versatile connection positioning. To dispense with inclination on going by some exceedingly significant connections in shrouded web indexes, we outline a connection tree information structure to accomplish more extensive scope for a site. Our test results on an arrangement of delegate areas demonstrate the readiness and precision of our proposed crawler structure, which effectively recovers profound web interfaces from huge scale destinations and accomplishes higher harvest rates than different crawlers.
Applications of Artificial Neural Network in Forecasting of Stock Market Indexpaperpublications3
Abstract: Prediction in any field is a challenging and unnerving process. Stock market is a promising financial investment that can generate great wealth. However, under the impact of Globalization Stock Market Prediction (SMP) accuracy has become more challenging and rewarding for the researchers and participants in the stock market. Artificial Neural Networks (ANN) have been found to be an efficient tool in modeling stock prices and quite a large number of studies have been done on it. ANN modeling of stock prices of selected stocks under NSE is attempted to predict the next day’s price. The network developed consists of one input layer, hidden layer and output layer with four, nine and one nodes respectively. The input being the closing price of the previous four days and output being the price for the next day. In the first section the adaptability of neural networks in stock market prediction is discussed, in the second section we discuss the traditional methods that were being used earlier for stock market prediction, in the third section we discuss the justification for using neural networks and how it is better over traditional methods, in the fourth section we discuss the basics of neural networks, section five gives an overview of data and methodology being used, in section six we have discussed the various forecasting errors methods to calculate the error, in section seven we have presented our results. The aim of this paper is to provide an overview of the application of artificial neural network in stock market prediction.
Command Transfer Protocol (CTP) for Distributed or Parallel Computationpaperpublications3
Abstract: In this paper, an improved version of a new networking protocol CTP for distributed or parallel computations is presented. In common, it is suitable just for fast, reliable and feature full interchange of small messages. CTP is a transport level API which helps in incrementing the speed of interchange. CTP is designed to allow general configurability, enabling its use in a wide range of general purpose and specialized applications. CTP covers a number of layers, from transport layer to application layer, proves that the area of its responsibility starts from relatively low level and goes to a high one.
Pobreza, condição de nascença, desgraça, destinoLucas Castro
A empresa de tecnologia anunciou um novo smartphone com câmera aprimorada, processador mais rápido e bateria de maior duração. O dispositivo também possui tela maior e armazenamento expansível, com preço sugerido a partir de $599. Analistas esperam que o aparelho ajude a empresa a aumentar sua participação no competitivo mercado de smartphones.
The document discusses the benefits of exercise for mental health. Regular physical activity can help reduce anxiety and depression and improve mood and cognitive function. Exercise causes chemical changes in the brain that may help protect against developing mental illness and improve symptoms for those who already suffer from conditions like anxiety and depression.
The document discusses the unlikelihood of OPEC's proposed oil freeze plan taking effect by the end of 2016. It notes that while OPEC members agreed in September to potentially curb oil production, there are several indications this plan will not be implemented. Key factors include inconsistencies between meetings, reluctance of some countries to participate, and the lack of agreed upon production quotas. Given OPEC's poor track record with past agreements and uncertain market and demand conditions, most analysts believe a binding deal in 2016 is unlikely and actual reductions may not occur until 2017 if at all.
Este documento presenta 5 ejercicios de fórmulas en Excel. El primero muestra una fórmula para verificar si un número en la celda A1 es mayor o menor que 100. El segundo calcula el IVA de un subtotal en la celda A5, siempre que sea mayor a 10, de lo contrario muestra un mensaje. El tercero identifica si un número en A5 es par o impar. El cuarto indica si un dato en A5 corresponde a un usuario mayor o menor de edad.
O documento descreve a evolução do sistema operacional Android da Google, mencionando as versões KitKat 4.4, Jelly Bean 4.1 e 4.3, e descrevendo brevemente os recursos básicos do Android, como acesso a aplicativos de entretenimento, mapas, armazenamento e e-mail.
Literature Review On: ”Speech Emotion Recognition Using Deep Neural Network”IRJET Journal
The document discusses speech emotion recognition using deep neural networks. It first provides an overview of SER and the challenges in the field. It then reviews 20 research papers on the topic, finding that most use deep neural network techniques like CNNs and DNNs for model building. The papers evaluated various datasets and algorithms, with accuracy ranging from 84% to 90%. Overall limitations identified included the need for more data, handling of multiple simultaneous emotions, and improving cross-corpus performance. The literature review contributes to knowledge in using machine learning for SER.
Signal Processing Tool for Emotion Recognitionidescitation
In the course of realization of modern day robots,
which not only perform tasks, but also behaves like human
beings during their interaction with the natural environment,
it is essential for us to impart knowledge of the underlying
emotions in the spoken utterances of human beings to the
robots, enabling them to be consistent, whole, complete and
perfect. To this end, it is essential for them too to understand
and identify the human emotions. For this reason, stress is
laid now-a-days on the study of emotional content of the speech
and accordingly speech emotion recognition engines have been
proposed. This paper is a survey of the main aspects of speech
emotion recognition, namely, features extractions and types
of features commonly used, selection of most informed
features from the original dataset of the features, and
classification of the features according to different classifying
techniques based on relative information regarding commonly
used database for the speech emotion recognition.
This document summarizes a study on the impact of emotion on prosody analysis in speech. The study analyzed speech samples recorded from actors expressing different emotions like love, anger, calm, sadness and neutral. It measured acoustic parameters like vowel duration, fundamental frequency, jitter and shimmer for the different emotions. The results showed that speech expressing love had longer vowel durations, while sad speech had longer durations for certain vowels. This indicates emotion impacts prosodic features of speech, which is important for applications like speech recognition and synthesis systems.
Emotion recognition based on the energy distribution of plosive syllablesIJECEIAES
We usually encounter two problems during speech emotion recognition (SER): expression and perception problems, which vary considerably between speakers, languages, and sentence pronunciation. In fact, finding an optimal system that characterizes the emotions overcoming all these differences is a promising prospect. In this perspective, we considered two emotional databases: Moroccan Arabic dialect emotional database (MADED), and Ryerson audio-visual database on emotional speech and song (RAVDESS) which present notable differences in terms of type (natural/acted), and language (Arabic/English). We proposed a detection process based on 27 acoustic features extracted from consonant-vowel (CV) syllabic units: \ba, \du, \ki, \ta common to both databases. We tested two classification strategies: multiclass (all emotions combined: joy, sadness, neutral, anger) and binary (neutral vs. others, positive emotions (joy) vs. negative emotions (sadness, anger), sadness vs. anger). These strategies were tested three times: i) on MADED, ii) on RAVDESS, iii) on MADED and RAVDESS. The proposed method gave better recognition accuracy in the case of binary classification. The rates reach an average of 78% for the multi-class classification, 100% for neutral vs. other cases, 100% for the negative emotions (i.e. anger vs. sadness), and 96% for the positive vs. negative emotions.
This document discusses an analysis of an emotion recognition system through speech signals using K-nearest neighbors (KNN) and Gaussian mixture model (KNN) classifiers. It provides background on the challenges of automatic emotion recognition from speech and describes common features extracted from speech like mel frequency cepstrum coefficients and prosodic features. The document outlines the process of an emotion recognition system including feature extraction, training classifiers on a speech database, and classifying emotions. It then gives more detail on the KNN and GMM classifiers and how they were used to classify six emotional states from the Berlin emotional speech database.
EPIDEMIC OUTBREAK PREDICTION USING ARTIFICIAL INTELLIGENCEijcsit
Intelligent Models for predicting diseases whether building a model to help the doctor or even preventing its spread in an area globally, is increasing day by day. Here we present a noble approach to predict the disease prone area using the power of Text Analysis and Machine Learning. Epidemic Search model using the power of the social network data analysis and then using this data to provide a probability score of the spread and to analyse the areas whether going to suffer from any epidemic spread-out, is the main focus of this work. We have tried to analyse and showcase how the model with different kinds of pre-processing and algorithms predict the output. We have used the combination of words-n grams, word embeddings and TFIDF with different data mining and deep learning algorithms like SVM, Naïve Bayes and RNN-LSTM. Naïve Bayes with TF-IDF performed better in comparison to others.
Text to Emotion Extraction Using Supervised Machine Learning TechniquesTELKOMNIKA JOURNAL
Proliferation of internet and social media has greatly increased the popularity of text
communication. People convey their sentiment and emotion through text which promotes lively
communication. Consequently, a tremendous amount of emotional text is generated on different social
media and blogs in every moment. This has raised the necessity of automated tool for emotion mining from
text. There are various rule based approaches of emotion extraction form text based on emotion intensity
lexicon. However, creating emotion intensity lexicon is a time consuming and tedious process. Moreover,
there is no hard and fast rule for assigning emotion intensity to words. To solve these difficulties, we
propose a machine learning based approach of emotion extraction from text which relies on annotated
example rather emotion intensity lexicon. We investigated Multinomial Naïve Bayesian (MNB) Classifier,
Artificial Neural Network (ANN) and Support Vector Machine (SVM) for mining emotion from text. In our
setup, SVM outperformed other classifiers with promising accuracy.
Intelligent Models for predicting diseases whether building a model to help the doctor or even preventing its spread in an area globally, is increasing day by day. Here we present a noble approach to predict the disease prone area using the power of Text Analysis and Machine Learning. Epidemic Search model using the power of the social network data analysis and then using this data to provide a probability score of the spread and to analyse the areas whether going to suffer from any epidemic spread-out, is the main focus of this work. We have tried to analyse and showcase how the model with different kinds of pre-processing and algorithms predict the output. We have used the combination of words-n grams, word embeddings and TFIDF with different data mining and deep learning algorithms like SVM, Naïve Bayes and RNN-LSTM. Naïve Bayes with TF-IDF performed better in comparison to others.
“C’mon – You Should Read This”: Automatic Identification of Tone from Languag...Waqas Tariq
Information extraction researchers have recently recognized that more subtle information beyond the basic semantic content of a message can be communicated via linguistic features in text, such as sentiments, emotions, perspectives, and intentions. One way to describe this information is that it represents something about the generator’s mental state, which is often interpreted as the tone of the message. A current technical barrier to developing a general-purpose tone identification system is the lack of reliable training data, with messages annotated with the message tone. We first describe a method for creating the necessary annotated data using human-based computation, based on interactive games between humans trying to generate and interpret messages conveying different tones. This draws on the use of game with a purpose methods from computer science and wisdom of the crowds methods from cognitive science. We then demonstrate the utility of this kind of database and the advantage of human-based computation by examining the performance of two machine learning classifiers trained on the database, each of which uses only shallow linguistic features. Though we already find near-human levels of performance with one classifier, we also suggest more sophisticated linguistic features and alternate implementations for the database that may improve tone identification results further.
This document discusses issues in sentiment analysis and emotion extraction from text. It provides an overview of different techniques used for emotion extraction like text mining, empirical studies, emotion extraction engines, and vector space models. It then analyzes the issues with each technique, such as only identifying the subject but not sentiment, inability to determine intensity, and difficulties with contradictory or symbolic text. The document concludes that combining the study of multiple techniques and parameters could help develop a more accurate system for sentiment analysis that is closer to realistic human emotion extraction from text.
Facial Expression Recognition System: A Digital Printing Applicationijceronline
International Journal of Computational Engineering Research (IJCER) is dedicated to protecting personal information and will make every reasonable effort to handle collected information appropriately. All information collected, as well as related requests, will be handled as carefully and efficiently as possible in accordance with IJCER standards for integrity and objectivity.
Facial Expression Recognition System: A Digital Printing Applicationijceronline
International Journal of Computational Engineering Research (IJCER) is dedicated to protecting personal information and will make every reasonable effort to handle collected information appropriately. All information collected, as well as related requests, will be handled as carefully and efficiently as possible in accordance with IJCER standards for integrity and objectivity.
This document discusses emotion detection from text. It presents an emotion detection model that extracts emotion from text at the sentence level without relying on existing affect lexicons. The model detects emotion by searching for direct emotional keywords and emotion-affect words/phrases. Experiments show the method achieves over 77% accuracy in detecting Ekman's six basic emotions from text. The document also reviews related work on emotion detection approaches, including keyword-based, rule-based, and machine learning methods. It discusses challenges like the lack of large annotated training data and limitations of dictionary-based approaches.
This document describes research on detecting emotions from speech in order to drive facial expressions of virtual characters. It discusses using support vector machines trained on a corpus of over 700 utterances expressing neutral, anger, happiness, or sadness emotions captured from movies and plays. The researchers propose evaluating emotions in speech as mixtures of multiple emotions based on their locations in an emotion space, rather than solely classifying utterances into single emotion categories. This allows them to determine the degree and combination of emotions expressed.
A Survey on Speech Recognition with Language Specificationijtsrd
As a cross disciplinary, speech recognition is entirely based on the speech as the survey object. Speech recognition allows the machine to convert the speech signal into text or commands via the process of identification and understanding. Speech recognition involves in various fields of physiology, psychology, linguistics, computer science and signal processing, and is even related to the person’s body language, and its goal is to achieve natural language communication between man and machine. The speech recognition technology is gradually becoming the key technology of the IT man machine interface. This paper describes the development of speech recognition technology and its basic principles, methods, reviewed the classification of speech recognition systems, speech recognition approaches and voice recognition technology, analyzed the problems faced by the speech recognition. Dr. Preeti Savant | Lakshmi Sandhya H "A Survey on Speech Recognition with Language Specification" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-6 | Issue-3 , April 2022, URL: https://www.ijtsrd.com/papers/ijtsrd49370.pdf Paper URL: https://www.ijtsrd.com/computer-science/speech-recognition/49370/a-survey-on-speech-recognition-with-language-specification/dr-preeti-savant
Emotion Detection is one of the most emerging issues in human computer interaction. A sufficient amount
of work has been done by researchers to detect emotions from facial and audio information whereas
recognizing emotions from textual data is still a fresh and hot research area. This paper presented a
knowledge based survey on emotion detection based on textual data and the methods used for this purpose.
At the next step paper also proposed a new architecture for recognizing emotions from text document.
Proposed architecture is composed of two main parts, emotion ontology and emotion detector algorithm.
Proposed emotion detector system takes a text document and the emotion ontology as inputs and produces
one of the six emotion classes (i.e. love, joy, anger, sadness, fear and surprise) as the output.
Emotion detection on social media status in Myanmar language IJECEIAES
Many social media emerged and provided services during these years. Most people, especially in Myanmar, use them to express their emotions or moods, learn subjects, sell products, read up-to-date news, and communicate with each other. Emotion detection on social users makes critical tasks in the opinion mining and sentiment analysis. This paper presents the emotion detection system on social media (Facebook) user status or post written in Myanmar (Burmese) language. Before the emotion detection process, the user posts are pre-processed under segmentation, stemming, part-of-speech (POS) tagging, and stop word removal. The system then uses our preconstructed Myanmar word-emotion Lexicon, M-Lexicon, to extract the emotion words from the segmented POS post. The system provides six types of emotion such as surprise, disgust, fear, anger, sadness, and happiness. The system applies naïve Bayes (NB) emotion classifier to examine the emotion in the case of more than two words with different emotion values are extracted. The classifiers also classify the emotion of the users on their posts. The experiment shows that the system can detect 85% accuracy in NB based emotion detection while 86% in recurrent neural network (RNN).
Emotion Detection from Voice Based Classified Frame-Energy Signal Using K-Mea...ijseajournal
Emotion detection is a new research era in health informatics and forensic technology. Besides having some challenges, voice based emotion recognition is getting popular, as the situation where the facial image is not available, the voice is the only way to detect the emotional or psychiatric condition of a
person. However, the voice signal is so dynamic even in a short-time frame so that, a voice of the same person can differ within a very subtle period of time. Therefore, in this research basically two key criterion have been considered; firstly, this is clear that there is a necessity to partition the training data according
to the emotional stage of each individual speaker. Secondly, rather than using the entire voice signal, short time significant frames can be used, which would be enough to identify the emotional condition of the speaker. In this research, Cepstral Coefficient (CC) has been used as voice feature and a fixed valued kmeans clustered method has been used for feature classification. The value of k will depend on the number
of emotional situations in human physiology is being an evaluation. Consequently, the value of k does not necessarily consider the volume of experimental dataset. In this experiment, three emotional conditions: happy, angry and sad have been detected from eight female and seven male voice signals. This methodology has increased the emotion detection accuracy rate significantly comparing to some recent works and also reduced the CPU time of cluster formation and matching.
Signal & Image Processing : An International Journal sipij
Signal & Image Processing : An International Journal is an Open Access peer-reviewed journal intended for researchers from academia and industry, who are active in the multidisciplinary field of signal & image processing. The scope of the journal covers all theoretical and practical aspects of the Digital Signal Processing & Image processing, from basic research to development of application.
Authors are solicited to contribute to the journal by submitting articles that illustrate research results, projects, surveying works and industrial experiences that describe significant advances in the areas of Signal & Image processing.
Advanced control scheme of doubly fed induction generator for wind turbine us...IJECEIAES
This paper describes a speed control device for generating electrical energy on an electricity network based on the doubly fed induction generator (DFIG) used for wind power conversion systems. At first, a double-fed induction generator model was constructed. A control law is formulated to govern the flow of energy between the stator of a DFIG and the energy network using three types of controllers: proportional integral (PI), sliding mode controller (SMC) and second order sliding mode controller (SOSMC). Their different results in terms of power reference tracking, reaction to unexpected speed fluctuations, sensitivity to perturbations, and resilience against machine parameter alterations are compared. MATLAB/Simulink was used to conduct the simulations for the preceding study. Multiple simulations have shown very satisfying results, and the investigations demonstrate the efficacy and power-enhancing capabilities of the suggested control system.
Null Bangalore | Pentesters Approach to AWS IAMDivyanshu
#Abstract:
- Learn more about the real-world methods for auditing AWS IAM (Identity and Access Management) as a pentester. So let us proceed with a brief discussion of IAM as well as some typical misconfigurations and their potential exploits in order to reinforce the understanding of IAM security best practices.
- Gain actionable insights into AWS IAM policies and roles, using hands on approach.
#Prerequisites:
- Basic understanding of AWS services and architecture
- Familiarity with cloud security concepts
- Experience using the AWS Management Console or AWS CLI.
- For hands on lab create account on [killercoda.com](https://killercoda.com/cloudsecurity-scenario/)
# Scenario Covered:
- Basics of IAM in AWS
- Implementing IAM Policies with Least Privilege to Manage S3 Bucket
- Objective: Create an S3 bucket with least privilege IAM policy and validate access.
- Steps:
- Create S3 bucket.
- Attach least privilege policy to IAM user.
- Validate access.
- Exploiting IAM PassRole Misconfiguration
-Allows a user to pass a specific IAM role to an AWS service (ec2), typically used for service access delegation. Then exploit PassRole Misconfiguration granting unauthorized access to sensitive resources.
- Objective: Demonstrate how a PassRole misconfiguration can grant unauthorized access.
- Steps:
- Allow user to pass IAM role to EC2.
- Exploit misconfiguration for unauthorized access.
- Access sensitive resources.
- Exploiting IAM AssumeRole Misconfiguration with Overly Permissive Role
- An overly permissive IAM role configuration can lead to privilege escalation by creating a role with administrative privileges and allow a user to assume this role.
- Objective: Show how overly permissive IAM roles can lead to privilege escalation.
- Steps:
- Create role with administrative privileges.
- Allow user to assume the role.
- Perform administrative actions.
- Differentiation between PassRole vs AssumeRole
Try at [killercoda.com](https://killercoda.com/cloudsecurity-scenario/)
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
An improved modulation technique suitable for a three level flying capacitor ...IJECEIAES
This research paper introduces an innovative modulation technique for controlling a 3-level flying capacitor multilevel inverter (FCMLI), aiming to streamline the modulation process in contrast to conventional methods. The proposed
simplified modulation technique paves the way for more straightforward and
efficient control of multilevel inverters, enabling their widespread adoption and
integration into modern power electronic systems. Through the amalgamation of
sinusoidal pulse width modulation (SPWM) with a high-frequency square wave
pulse, this controlling technique attains energy equilibrium across the coupling
capacitor. The modulation scheme incorporates a simplified switching pattern
and a decreased count of voltage references, thereby simplifying the control
algorithm.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
Batteries -Introduction – Types of Batteries – discharging and charging of battery - characteristics of battery –battery rating- various tests on battery- – Primary battery: silver button cell- Secondary battery :Ni-Cd battery-modern battery: lithium ion battery-maintenance of batteries-choices of batteries for electric vehicle applications.
Fuel Cells: Introduction- importance and classification of fuel cells - description, principle, components, applications of fuel cells: H2-O2 fuel cell, alkaline fuel cell, molten carbonate fuel cell and direct methanol fuel cells.
1. ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Vol. 3, Issue 1, pp: (82-89), Month: April 2016 – September 2016, Available at: www.paperpublications.org
Page | 82
Paper Publications
Voice Emotion Recognition
Ankita Kirti, Nishant Anand
Abstract: Speech technology and systems in human computer interaction have witnessed a stable and remarkable
advancement over the last two decades. Today, speech technologies are commercially available for an unlimited
but interesting range of tasks. These technologies enable machines to respond correctly and reliably to human
voices, and provide useful and valuable services. This thesis presents the characteristics of emotion in voice and on
that basis propose a new method to detecting emotion in a simplified way by using a prosodic features and spectral
from speech. We classify seven emotions: happy, anger, fear, disgust, sadness and neutral inner state. This thesis
discusses the method to extract features from a recorded speech sample, and using those features, to detect the
emotion of the subject. Every emotion comprises different vocal parameters exhibiting diverse characteristics of
speech, which is used for preliminary classification. Then Mel-Frequency Cepstrum Coefficient (MFCC) method
was used to extract spectral features. The MFCC coefficients were again trained by Artificial Neural Network
(ANN) which then classifies the input in particular emotional class.
Keywords: Speech technology, MFCC, Artificial Neural Network.
1. INTRODUCTION
Automatic Emotion Recognition is a recent research topic which is primarily formulated for the Human Computer
Interaction (HCI) field. As computers have become an integral part of our lives, the need has risen for more natural
communication interface between human beings. To make HCI more natural, it would be favourable if modelled systems
have the ability to recognize emotional situations the same way as humans do. It is very easy to understand the emotions
of our known ones because we are accustomed to the habits and activities of them, but when we interact with a stranger,
our mind reads their voice and predict their emotion by matching the acoustic patterns of voice with previously
encountered voice patterns. Similarly if a robot needs to interact with the humans, they should be able to read the
emotions of people interacting with them.
1.1 Literature Survey
Recent research concentrates on developing systems that would be much more robust against variability in environment,
speaker and language.
This thesis discusses approaches to recognize the emotional user state by analyzing spoken utterances on both, the
semantic and the signal level. We classify seven emotions: happy, anger, surprise, fear, disgust, sadness and neutral inner
state.
Human Machine Interface (HMI) recognition systems incorporate the principles of corporal interaction that deduce
perfunctory characteristic extraction methods. The speech characteristics include pitch, formant, prosody and timbre. The
emotion verification task designed for such recognition systems uses a-priori information to determine whether the
outcome of a speech sample is efficiently construed in a manner in which the sentence is spoken. In practice, a-priori
information would normally be available in a real system, instinctively captured when candidate users are registered with
that system. Within such constraints, there are two further main branches to this research area; one in which the material
being spoken is fixed and the other in which the material being spoken is unrestricted. In the unrestricted case the problem
is more difficult, and accuracy may be more closely related to the amount of captured data that can be analysed than upon
the accuracy of the system employed[1].
2. ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Vol. 3, Issue 1, pp: (82-89), Month: April 2016 – September 2016, Available at: www.paperpublications.org
Page | 83
Paper Publications
The first book on expression of emotions in animals and humans was written by Charles Darwin in the nineteenth century
[1]. After this milestone work psychologists have gradually
accumulated knowledge in the field. A new wave of interest has recently risen attracting both psychologists and artificial
intelligence specialists. There are several reasons for this renaissance such as: technological progress in recording, storing,
and processing audio and visual information; the development of non-intrusive sensors; the advent of wearable
computers; the urge to enrich human-computer interface from point-and-click to sense-and-feel; and the invasion on our
computers of lifelike software agents and in our homes robotic animal-like devices like Tiger’s Furbies and Sony’s Aibo
who supposed to be able express, have and understand emotions. A new field of research in AI known as affective
computing has recently been identified [2]. As to research on decoding and portraying emotions in speech, on one hand,
psychologists have done many experiments and suggested theories (reviews of about 60 years of research can be found in
[3,4]). On the other hand, AI researchers made contributions in the following areas: emotional speech synthesis [5],
recognition of emotions [6], and using agents for decoding and expressing emotions [7]. The motivation for our research
is to explore the ways how recognition of emotions in speech could be used for business, in particular, in a call center
environment. One potential application is the detection of the emotional state in telephone conversations, and providing a
feedback to an operator or a supervisor for monitoring purposes. Another application is sorting voice mail messages
according to the emotions expressed by the caller. One more challenging problem is to use emotional content of the
conversation for the operator performance evaluation.
In the computer speech community, much attention has been given to “what was said” and “who said it”, and the
associated tasks of speech recognition and speaker identification, whereas “how it was said” has received relatively little.
Previous research on emotions both in psychology and speech tell us that we can find information associated with
emotions from a combination of prosodic, tonal and spectral information; speaking rate and stress distribution also
provide some clues about emotions [2]
1.2 Motivation
Speech is one of the most natural communication forms between human beings. Humans also express their emotion via
written and spoken language. Enabling systems to interpret user utterances for a more intuitive human machine interaction
therefore suggests also understanding transmitted emotional aspects. The actual user emotion may help system track the
user's behaviour by adapting to his inner mental state. Generally recognition of emotions is in the scope of research in the
human-machine-interaction. Among other modalities like mimic speech is one of the most promising and established
modalities for the recognition [1][2][3]. There are several emotional hints carried within the speech signal. Nowadays
attempts in detecting emotional speech analyze in general signal characteristics like pitch, energy, duration or spectral
distortions [4]. However, on semantically higher levels emotional clues can also be found. In literature one can even rely
almost only on such semantic hints besides spare graphical attempts to capture prosodic elements like in bold or italic
characters typed phrases. Therefore we aim to also spot emotional keyphrases, analyze the dialogue history and the degree
of verbosity in the communication between man and machine. This is realized through a parallel analysis of spoken
utterances in view of general system announcements, command interpretation and detection of emotional aspects.
However, the semantic means introduced could as well be used for analysis of nonspoken language.
Emotions are fundamental for humans, impacting perception and everyday activities such as communication, learning and
decision-making. They are expressed through speech, facial expressions, gestures and other non-verbal clues. Speech
emotion detection refers to analysing vocal behaviour as a marker of affect, with focus on the nonverbal aspects of
speech. Its basic assumption is that there is a set of objectively measurable parameters in voice the affective state a person
is currently expressing. This assumption is supported by the fact that most affective states involve physiological reactions
which in turn modify the process by which voice is produced. For example, anger often produces changes in respiration
and increases muscle tension, inuencing the vibration of the vocal folds and vocal tract shape and affecting the acoustic
characteristics of the speech [25]. So far, vocal emotion expression has received less attention than the facial equivalent,
mirroring the relative emphasis by pioneers such as Charles Darwin.
In the past, emotions were considered to be hard to measure and were consequently not studied by computer scientists.
Although the field has recently received an increase in contributions, it remains a new area of study with a number of
potential applications. These include emotional hearing aids for people with autism; detection of an angry caller at an
3. ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Vol. 3, Issue 1, pp: (82-89), Month: April 2016 – September 2016, Available at: www.paperpublications.org
Page | 84
Paper Publications
automated call centre to transfer to a human; or presentation style adjustment of a computerised e-learning tutor if the
student is bored. A new application of emotion detection proposed in this dissertation is speech tutoring. Especially in
persuasive communication, special attention is required to what non-verbal clues the speaker conveys. Untrained speakers
often come across as bland, lifeless and colourless. Precisely measuring and analysing the voice is a difficult task and has
in the past been entirely subjective. By using a similar approach as for detecting emotions, this report shows that such
judgements can be made objective.
1.3 Challenges
This section describes some of the expected challenges in implementing a realtime speech emotion detector. Firstly,
discovering which features are indicative of emotion classes is a difficult task. The key challenge, in emotion detection
and in pattern recognition in general, is to maximise the between-class variability whilst minimising the within class
variability so that classes are well separated. However, features indicating different emotional states may be overlapping,
and there may be multiple ways of expressing the same emotional state. One strategy is to compute as many features as
possible. Optimisation algorithms can then be applied to select the features contributing most to the discrimination while
ignoring others, creating a compact emotion code that can be used for classiffication. This avoids making difficult a priori
assumptions about which features may be relevant. Secondly, previous studies indicate that several emotions can occur
simultaneously [14]. For example, co-occurring emotions could include being happy at the same time as being tired, or
feeling touched, surprised and excited when hearing good news. This requires a classiffier that can infer multiple
temporally co-occurring emotions. Thirdly, real-time classiffication will require choosing and implementing efficient
algorithms and data structures. Despite there existing some working systems, implementations are still seen as challenging
and are generally expected to be imperfect and imprecise.
2. EMOTIONS AND THEIR ACOUSTIC FEATURES
There has not been any considerable published matter about the properties of the emotional states of speech orated. The
different emotions are characterised by specific properties which vary from person to person, but on an average the
properties of every emotion can be distinguished from other.
A short description is being given below which is dominant in normal emotional voices:
Anger: Anger is characterised by many high tones in speech, fast rate of speaking with little and negligible pauses.
Happy: Lot much air is also expelled out in happiness as we tend to laugh. The tones are high but not similar to angry
speech, resulting in slightly lower mean values.
Fear: The voice becomes shaky with low rate of speech because of inability to think quick, but there is a good
combination of quick high and low tone changes.
Sad: Sad voice has the lowest values for all the properties. The rate becomes slow, speaker uses low tones unable to hear
and we find seldom use of high tones;
Surprise: The sentences start with high tone out of excitement, but decreases along the length of sentence. The voice
possess similar rate of speech as the normal voice.
Disgust: It has much similarity with sad voice, but is has got some uses of high tones at instances to express the disgust
when talking about a specific subject. It specially varies when cause is being discussed.
Normal: It enjoys a moderate rate of speech, easily understandable by all. The words are pronounces in a monotonous
tone, because of lack of emotions.
A comparative study is shown below on the very basic properties of speech:
Table 1.Comparision of Prosodic features of Emotions
Anger Happy Fear Sad Surprise Disgust Normal
Mean More More More Less More Less Less
Std. Deviation Less Mid More Less Less Mid Less
Rate of Speech More More Less Less Mid Mid Mid
4. ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Vol. 3, Issue 1, pp: (82-89), Month: April 2016 – September 2016, Available at: www.paperpublications.org
Page | 85
Paper Publications
These characterstics are present in normal portrayal of emotion, provided any problem in speech of individuals. The
challenging problem is mimicked speech which is one of the most promising for the recognition [6].
3. FEATURES EXTRACTION OF SPEECH
Feature extraction is the process of calculating the speech signal features which are relevant for speech processing. Since
the computer has no sense of hearing and perception like humans, they have to be fed with these features of speech which
become a determining factor after classification. Feature extraction involves analysis of speech signal. The researchers
have used various features such as pitch, loudness, MFCC, LPC etc for extracting emotion. The number of features range
from 39 extracted from mfcc to few hundreds including formants, maximum, minimum, standard deviation and so on for
improving the correctness of results. The feature extraction techniques are classified as temporal analysis and spectral
analysis technique. In temporal analysis, the speech waveform itself is used for analysis. In spectral analysis, the spectral
representation of speech signal is used for analysis. Features are primary indicator of speaker’s emotional state. A lot of
features are extracted from feature extraction process like Mel Frequency Cepstral Coefficient (MFCC), pitch, PLP,
RASTA-PLP, loudness etc. Feature extraction process can be divided into two steps: spectral feature extraction and
prosodic feature extraction.
A. Spectral Feature Extraction
1. MFCC
The MFCC [1] is the most relevant example of a feature set that is extensively used in voice processing. Speech is usually
segmented in frames of 20 to 30 ms, and the window analysis is shifted by 10 ms.Each frame is transformed to 12 MFCCs
plus a normalized energy parameter. The first and second derivatives (D’s and DD’s) of MFCCs and energy are estimated,
resulting in 39 numbers that represent each frame. Assuming sample rate of 8 kHz, for each 10 ms the feature extraction
module delivers 39 numbers to the modelling stage. This operation with overlap among frames is equivalent to taking 80
speech samples without overlap and representing them by 39 numbers. In fact, assuming that each speech sample is
represented by one byte and each feature is represented by four bytes (float number), one can see that the parametric
representation increases the number of bytes to represent 80 bytes of speech (to 136 bytes). If a sample rate of 16 kHz is
assumed, the 39 parameters would represent 160 samples. For higher sample rates, it is intuitive that 39 parameters do not
allow reconstructing the speech samples back. Anyway, one should notice that goal here is not speech compression but
using features suitable for speech recognition.
The following figure shows steps involved in MFCC feature extraction.
Fig:1
Speech Signal
MFCC Feature Vector
Hamming Window
DFT
Outputenergy of
filters onMel-scale
LOGInverse DFTMel Cepstrum
5. ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Vol. 3, Issue 1, pp: (82-89), Month: April 2016 – September 2016, Available at: www.paperpublications.org
Page | 86
Paper Publications
MFCCs are the most widely used spectral representation of speech in many applications, including speech emotion
recognition because statistics relating to MFCCs also carry emotional information.
2. LPC
It is one of the powerful signal analysis techniques is the method of linear prediction. Linear predictive coding (LPC) is a
tool used mostly in audio signal processing and speech processing for representing the spectral envelope of a digital signal
of speech in compressed form, using information of a linear predictive model [2]. It provides an accurate estimate of the
speech parameters and it is also an efficient computational model of speech. The idea behind LPC is that a speech sample
can be approximated as a linear combination of past speech samples. Through minimizing the amount of squared
differences (over a finite interval) between the actual speech samples and predicted values, a unique set of parameters, the
predictor coefficients can be determined. These coefficients form the basis of LPC of speech [3]. The analysis provides
the capability for computing the linear prediction model of speech over time. Predictor coefficients are therefore
transformed to a robust set of parameters known as cepstral coefficients. Figure 2 shows the steps involved in LPC feature
extraction.
FIG 2
B. Prosodic Feature Extraction
1. Pitch
Statistics related to pitch [13] conveys considerable information about emotional status. For this project, pitch is extracted
from the speech waveform using a modified version of the RAPT algorithm for pitch tracking implemented in the
VOICEBOX toolbox. Using a frame length of 50ms, the pitch for each frame was calculated and placed in a vector to
correspond to that frame. The various statistical features are extracted from the pitch tracked from the samples. We use
minimum value, maximum value, range and the moments- mean, variance, skewness and kurtosis. We hence get a 7
dimensional feature vector which is appended to the end of the 39 dimensional supervector obtained from the GMM.
2. Loudness
Loudness [14] is extracted from the samples using DIN45631 implementation of loudness model in MATLAB. The
function loudness() returns loudness for each frame length of 50ms and also one single specific loudness value. Now the
same minimum value, maximum value, range and the moments- mean, variance, skewness and kurtosis statistical features
are used to model the loudness vector. Hence we get an 8 dimensional feature vector which is appended to the already
obtained 46 dimensional feature vector to obtain the final 54 dimensional feature vector. This vector can now be given as
input to the SVM.
3. Formant
Formants are the distinguishing or meaningful frequency components of human speech and of singing. By definition, the
information that a human requires to distinguish between vowels can be represented purely quantitatively by the frequency
content of the vowel sounds. In speech, these are characteristic partials that identify vowels to the listener. The formant
with lowest frequency is called f1, the second lowest called f2, and the third f3. Most often the first two formants, f1 and f2,
are enough to disambiguate a vowel. These two formants determine quality of vowels in terms of the open/close and
front/back dimensions (which have traditionally, though not accurately, been associated with position of the tongue). Thus
first formant f1 has a higher frequency for an open vowel (such as [a]) and a lower frequency for a close vowel (such as [i]
LP
Analysis
Frame
Blocking
Windowing
Auto Correlation
Analysis
Speech
Signal
LPC Feature
Vectors
6. ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Vol. 3, Issue 1, pp: (82-89), Month: April 2016 – September 2016, Available at: www.paperpublications.org
Page | 87
Paper Publications
or [u]); and the second formant f2 has a higher frequency for a front vowel (such as [i]) and a lower frequency for a back
vowel (such as [u]).[15][16] Vowels will almost always have four or more distinguishable formants; sometimes there are
more than six. However, the first two formants are the most important in determining vowel quality, and this is displayed in
terms of a plot of the first formant against the second formant,[17] though this is not sufficient to capture some aspects of
vowel quality, such as rounding.[18]
Nasals usually have an additional formant around 2500 Hz. The liquid [l] usually has an extra formant at 1500 Hz, while
the English "r" sound ([ɹ]) is distinguished by virtue of a very low third formant (well below 2000 Hz).
Plosives (and, to some degree, fricatives) modify the placement of formants in the surrounding vowels. Bilabial sounds
(such as /b/ and /p/ in "ball" or "sap") cause a lowering of the formants; velar sounds (/k/ and /g/ in English) almost always
show f2 and f3 coming together in a 'velar pinch' before the velar and separating from the same 'pinch' as the velar is
released; alveolar sounds (English /t/ and /d/) cause less systematic changes in neighboring vowel formants, depending
partially on exactly which vowel is present. The time-course of the changes in vowel formant frequencies are referred to as
'formant transitions'.
If the fundamental frequency of the underlying vibration is higher than a resonance frequency of system, then the formant
usually imparted by that resonance will be mostly lost. This is most apparent in example of soprano opera singers, who sing
high enough that their vowels seem to be very hard to distinguish.
4. IMPLEMENTATION AND RESULTS
The emotions were acted, what surely is a disadvantage since users tend to exaggerate when acting. In an initial phase
user statements were not recorded to make the pro-bands familiar with simulating emotions naturally. For the
classification of prosodic parameters the system was in advance adapted by training with ten samples for each emotion.
However, these results can be seen as upper limit for achievable results.
The confusion between anger fear and surprise is high in comparison with any other pair of emotion. This is due to the
fact that the features such as pitch acoustic features of these two emotions are considerably different to other emotions.
The back-propagation algorithm proves to be an efficient method for emotion recognition with reference to the graphical
result. The detection of anger, fear and surprise is above 80%. The normal, sad and happy voice detection is fairly good.
The detection of disgust shows the lowest results.
Table II: Confusion-Matrix obtained for the detection of emotion
Emotional
Class
Sad Anger Fear Surprise Disgust Happy Normal
Sad 70.11% 10.48% 6.02% 1.50% 7.50% 0.5% 3.99%
Anger 4.5% 86.55% 2.05% 0% 5.03% 1.47% 0.4%
Fear 5.98% 2.02% 83.67% 0.52% 1.48% 0.00% 6.33%
Surprise 1% 1.67% 1.33% 85.87% 0.23% 7.77% 2.13%
Disgust 26.72% 8.28% 1.44% 0.00% 60.98% 0.56% 2.02%
Happy 0.00% 0.00% 2.06% 4.96% 3.2% 78.34% 11.46%
Normal 5.94% 2.44% 1.5% 1.06% 1.05% 10.89% 77.12%
It could be shown that understanding emotional phrases seems a very promising way. However the combination with
prosodic parameters is useful to capture non-verbal expressions. Further semantic features could not be used to
satisfyingly detect all accosted emotions, but they also supported robust recognition in the fusion. Finally the fusion was
able to resolve ironic phrases by the signal characteristics. Generally the recognition proved rather speaker dependent, but
conditioning the system to a new user keeps the system applicable. The concept of integration of models allows the
connection of further multimodal input data as general human expressional characteristics like mimic recognition or
domain specific data like driving data in a car. The results highly motivate further investigation in this area.
The recognition system strictly adheres to the computed results of the database. The recognition of disgust remains the
most demanding problem. Rest emotions are recognised on an average at a rate of 75%.
7. ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Vol. 3, Issue 1, pp: (82-89), Month: April 2016 – September 2016, Available at: www.paperpublications.org
Page | 88
Paper Publications
The future of emotion recognition lies with solving the three low tone emotions that are the signs of Depression and
Crime in the society. The major health problems are due to the lack of emotional stability of persons that lead to suicide,
cardiac risks, and neurological problems and in a whole disruption in the growth of society and mankind.
5. FUTURE SCOPE
In the interpersonal communication partners adapt in their acoustic parameters to show sympathy for each other. A
technical system enabled to talk by speech synthesis therefore needs to know the actual user emotion and the according
acoustic parameters to adapt instead of staying neutral all the time. Furthermore the communication channels of a speaker
interact with each other. The knowledge of the implicit channel is needed to interpret the explicit channel. Irony might be
a good example to demonstrate that prosodic features help understand the explicitly uttered intention. An emotion
recognition system might also be called in for an objective judgment in psychiatric studies [5]. Finally there is certainly a
funfactor in automatic reaction to user emotions in many applications like video games.
In a first approach we used a two-dimensional emotion sphere defined by the axes activeness and positveness [7]. In this
plain different areas could be assigned to emotional states. For example a very active and positive user is meant to be
joyful, while an as well passive as negative user is associated with sadness. Other approaches introduce even a third
dimension [8] with an axis of control level. The basing measurement of the extent of positiveness or activeness however
turned out to be over-dimensioned. In a second approach we directly distinguished between seven basic emotional states
according to the MPEG-standard [9]: joy, anger, irritation, fear, disgust, sadness and neutral user state. This is also a far
spread classification of emotions with more or less states [10]. However, a provided confidence level of an assumed
emotion might still also be seen as a measurement of its extent.
The detected emotions recognized by the methods presented in this thesis are used in our man-machine interfaces. We
want to recognize errors in the man machine- interaction by a negative user emotion. If a user seems annoyed after a
system reaction error-recovery strategies are started. On the other hand a joyful user encourages a system to train user
models without supervision. First or higher order user preferences can be trained to constrain the potential intention
sphere for erroneously recognition instances like speech or gesture input. To do so a system online needs a reference value
like a positive user reaction. Furthermore our system initiatively provides help for a seemingly irritated user. Control or
induction of user emotions is another field of application that requires the knowledge of the actual emotion. For example
in high risk-tasks it seems useful to calm down a nervous person, do not distract her by shortening dialogues, or keep a
tired user awake.
REFERENCES
[1] L. Yang, “The expression of emotions through prosody”, ICSLP 2001, Beijing, China, Proc. Vol. 1, 2000, pp. 74-
77.
[2] W. Yoon, K. Park, A study of emotion recognition and its applications, in: Modeling Decisions for Artificial
Intelligence, vol. 6417, 2007, pp. 455–462.
[3] http://www.speech-therapy-information-and-resources.com/voice
[4] Yildirim, S., Bulut, M., Lee, C.M., Kazemzadeh, A., Busso, C., Deng, Z., Lee, S., Narayanan, S., 2004. An
acoustic study of emotions expressed in speech. In: Proc. Internat. Conf. on Spoken Language Processing (ICSLP
’04), Korea, Vol. 1, pp. 2193–2196.
[5] Schu¨ ller, B., Rigoll, G., Lang, M., 2004. Speech emotion recognition combining acoustic features and linguistic
information in a hybrid support vector machine-belief network architecture. In: Proc. Internat. Conf. on Acoustics,
Speech and Signal Processing (ICASSP ’04), Vol. 1, pp. 557–560.
[6] N. Amir, and S. Ron, “Towards an automatic classification of emotion in speech”, in Proc. of ICSLP, Sydney, Dec.
1998, pp. 555–558.
[7] Kwon O., Chan K., Hao J., Lee T. “Emotion Recognition by Speech Signals”, Proc. of Eurospeech. 2003, Genewa,
p. 125-128, September 2003.
8. ISSN 2350-1022
International Journal of Recent Research in Mathematics Computer Science and Information Technology
Vol. 3, Issue 1, pp: (82-89), Month: April 2016 – September 2016, Available at: www.paperpublications.org
Page | 89
Paper Publications
[8] L.R. Rabiner and B.H. Juang, Fundamentals of Speech Recognition, Prentice Hall.,1993
[9] L. Rabiner, B. H. Juang, “Prentice Hall”, Prentice Hall, 2010.
[10] Banse, R. and Scherer, K.R. Acoustic profiles in vocal emotion expression. Journal of Personality and Social
Psychology.70: 614-636, 1996; Scherer, K.R., 2000b. Emotion effects on voice and speech: paradigms and
approaches to evaluation. In: Proc. ISCA Workshop on Speech and Emotion, Belfast, invited paper; Scherer, K.R.,
2003. Vocal communication of emotion: a review of research paradigms. Speech Comm. 40, 227–256.
[11] Scherer, K.R., R. Banse, H.G. Wallbott, and T. Goldbeck. 1991. Vocal cues in Emotion Encoding and Decoding.
MorivarionandEmotion 15:123-148
[12] Goh,A.T.C., “Back-propagation neural networks for modelling complex systems”, Artificial Intelligence in
Engineering, vol.9, no.3, pp.143-151,1995.
[13] Schuller, G. Rigoll, M. Lang, Speech emotion recognition combining acoustic features and linguistic information
in a hybrid support vector machine belief network architecture, in: Proceedings of the IEEE International
Conference on Acoustics, Speech, and Signal Processing (ICASSP’04), vol. 1, IEEE, 2004, pp. 577–580.
[14] M. Gilke, P. Kachare , R. Kothalikar , V. Pius, M. Pednekar, Int. Con. Elec. Eng. Info. 49 (2012), 150-154
[15] V. Arulmozhi, International Journal of Wisdom Based Computing, Vol. 1 (2), August 2011, 59-60.
[16] http://personal.ee.surrey.ac.uk/Personal/P.Jackson/SAVEE/