This research paper reports preliminary results of data-driven modeling of segmentalphoneme duration for
Marathi. Classification and Regression Tree based data driven duration modeling for segmental duration
prediction is presented. A number of features are considered and their usefulness and relative contribution for
segmental duration prediction is assessed. Objective evaluation of the duration model, by root mean squared
prediction error and correlation between actual and predicted durations, is performed.
Dynamic Construction of Telugu Speech Corpus for Voice Enabled Text EditorWaqas Tariq
In recent decades speech interactive systems have gained increasing importance. Performance of an ASR system mainly depends on the availability of large corpus of speech. The conventional method of building a large vocabulary speech recognizer for any language uses a top-down approach to speech. This approach requires large speech corpus with sentence or phoneme level transcription of the speech utterances. The transcriptions must also include different speech order so that the recognizer can build models for all the sounds present. But, for Telugu language, because of its complex nature, a very large, well annotated speech database is very difficult to build. It is very difficult, if not impossible, to cover all the words of any Indian language, where each word may have thousands and millions of word forms. A significant part of grammar that is handled by syntax in English (and other similar languages) is handled within morphology in Telugu. Phrases including several words (that is, tokens) in English would be mapped on to a single word in Telugu.Telugu language is phonetic in nature in addition to rich in morphology. That is why the speech technology developed for English cannot be applied to Telugu language. This paper highlights the work carried out in an attempt to build a voice enabled text editor with capability of automatic term suggestion. Main claim of the paper is the recognition enhancement process developed by us for suitability of highly inflecting, rich morphological languages. This method results in increased speech recognition accuracy with very much reduction in corpus size. It also adapts Telugu words to the database dynamically, resulting in growth of the corpus.
An Improved Approach for Word Ambiguity RemovalWaqas Tariq
Word ambiguity removal is a task of removing ambiguity from a word, i.e. correct sense of word is identified from ambiguous sentences. This paper describes a model that uses Part of Speech tagger and three categories for word sense disambiguation (WSD). Human Computer Interaction is very needful to improve interactions between users and computers. For this, the Supervised and Unsupervised methods are combined. The WSD algorithm is used to find the efficient and accurate sense of a word based on domain information. The accuracy of this work is evaluated with the aim of finding best suitable domain of word. Keywords: Human Computer Interaction, Supervised Training, Unsupervised Learning, Word Ambiguity, Word sense disambiguation
Parameters Optimization for Improving ASR Performance in Adverse Real World N...Waqas Tariq
From the existing research it has been observed that many techniques and methodologies are available for performing every step of Automatic Speech Recognition (ASR) system, but the performance (Minimization of Word Error Recognition-WER and Maximization of Word Accuracy Rate- WAR) of the methodology is not dependent on the only technique applied in that method. The research work indicates that, performance mainly depends on the category of the noise, the level of the noise and the variable size of the window, frame, frame overlap etc is considered in the existing methods. The main aim of the work presented in this paper is to use variable size of parameters like window size, frame size and frame overlap percentage to observe the performance of algorithms for various categories of noise with different levels and also train the system for all size of parameters and category of real world noisy environment to improve the performance of the speech recognition system. This paper presents the results of Signal-to-Noise Ratio (SNR) and Accuracy test by applying variable size of parameters. It is observed that, it is really very hard to evaluate test results and decide parameter size for ASR performance improvement for its resultant optimization. Hence, this study further suggests the feasible and optimum parameter size using Fuzzy Inference System (FIS) for enhancing resultant accuracy in adverse real world noisy environmental conditions. This work will be helpful to give discriminative training of ubiquitous ASR system for better Human Computer Interaction (HCI). Keywords: ASR Performance, ASR Parameters Optimization, Multi-Environmental Training, Fuzzy Inference System for ASR, ubiquitous ASR system, Human Computer Interaction (HCI)
A survey of named entity recognition in assamese and other indian languagesijnlc
Named Entity Recognition is always important when dealing with major Natural Language Processing
tasks such as information extraction, question-answering, machine translation, document summarization
etc so in this paper we put forward a survey of Named Entities in Indian Languages with particular
reference to Assamese. There are various rule-based and machine learning approaches available for
Named Entity Recognition. At the very first of the paper we give an idea of the available approaches for
Named Entity Recognition and then we discuss about the related research in this field. Assamese like other
Indian languages is agglutinative and suffers from lack of appropriate resources as Named Entity
Recognition requires large data sets, gazetteer list, dictionary etc and some useful feature like
capitalization as found in English cannot be found in Assamese. Apart from this we also describe some of
the issues faced in Assamese while doing Named Entity Recognition.
Survey on Indian CLIR and MT systems in Marathi LanguageEditor IJCATR
Cross Language Information Retrieval (CLIR) deals with retrieving relevant information stored in a language different from
the language of user’s query. This helps users to express the information need in their native languages. Machine translation based (MTbased)
approach of CLIR uses existing machine translation techniques to provide automatic translation of queries. This paper covers the
research work done in CLIR and MT systems for Marathi language in India.
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.
Dynamic Construction of Telugu Speech Corpus for Voice Enabled Text EditorWaqas Tariq
In recent decades speech interactive systems have gained increasing importance. Performance of an ASR system mainly depends on the availability of large corpus of speech. The conventional method of building a large vocabulary speech recognizer for any language uses a top-down approach to speech. This approach requires large speech corpus with sentence or phoneme level transcription of the speech utterances. The transcriptions must also include different speech order so that the recognizer can build models for all the sounds present. But, for Telugu language, because of its complex nature, a very large, well annotated speech database is very difficult to build. It is very difficult, if not impossible, to cover all the words of any Indian language, where each word may have thousands and millions of word forms. A significant part of grammar that is handled by syntax in English (and other similar languages) is handled within morphology in Telugu. Phrases including several words (that is, tokens) in English would be mapped on to a single word in Telugu.Telugu language is phonetic in nature in addition to rich in morphology. That is why the speech technology developed for English cannot be applied to Telugu language. This paper highlights the work carried out in an attempt to build a voice enabled text editor with capability of automatic term suggestion. Main claim of the paper is the recognition enhancement process developed by us for suitability of highly inflecting, rich morphological languages. This method results in increased speech recognition accuracy with very much reduction in corpus size. It also adapts Telugu words to the database dynamically, resulting in growth of the corpus.
An Improved Approach for Word Ambiguity RemovalWaqas Tariq
Word ambiguity removal is a task of removing ambiguity from a word, i.e. correct sense of word is identified from ambiguous sentences. This paper describes a model that uses Part of Speech tagger and three categories for word sense disambiguation (WSD). Human Computer Interaction is very needful to improve interactions between users and computers. For this, the Supervised and Unsupervised methods are combined. The WSD algorithm is used to find the efficient and accurate sense of a word based on domain information. The accuracy of this work is evaluated with the aim of finding best suitable domain of word. Keywords: Human Computer Interaction, Supervised Training, Unsupervised Learning, Word Ambiguity, Word sense disambiguation
Parameters Optimization for Improving ASR Performance in Adverse Real World N...Waqas Tariq
From the existing research it has been observed that many techniques and methodologies are available for performing every step of Automatic Speech Recognition (ASR) system, but the performance (Minimization of Word Error Recognition-WER and Maximization of Word Accuracy Rate- WAR) of the methodology is not dependent on the only technique applied in that method. The research work indicates that, performance mainly depends on the category of the noise, the level of the noise and the variable size of the window, frame, frame overlap etc is considered in the existing methods. The main aim of the work presented in this paper is to use variable size of parameters like window size, frame size and frame overlap percentage to observe the performance of algorithms for various categories of noise with different levels and also train the system for all size of parameters and category of real world noisy environment to improve the performance of the speech recognition system. This paper presents the results of Signal-to-Noise Ratio (SNR) and Accuracy test by applying variable size of parameters. It is observed that, it is really very hard to evaluate test results and decide parameter size for ASR performance improvement for its resultant optimization. Hence, this study further suggests the feasible and optimum parameter size using Fuzzy Inference System (FIS) for enhancing resultant accuracy in adverse real world noisy environmental conditions. This work will be helpful to give discriminative training of ubiquitous ASR system for better Human Computer Interaction (HCI). Keywords: ASR Performance, ASR Parameters Optimization, Multi-Environmental Training, Fuzzy Inference System for ASR, ubiquitous ASR system, Human Computer Interaction (HCI)
A survey of named entity recognition in assamese and other indian languagesijnlc
Named Entity Recognition is always important when dealing with major Natural Language Processing
tasks such as information extraction, question-answering, machine translation, document summarization
etc so in this paper we put forward a survey of Named Entities in Indian Languages with particular
reference to Assamese. There are various rule-based and machine learning approaches available for
Named Entity Recognition. At the very first of the paper we give an idea of the available approaches for
Named Entity Recognition and then we discuss about the related research in this field. Assamese like other
Indian languages is agglutinative and suffers from lack of appropriate resources as Named Entity
Recognition requires large data sets, gazetteer list, dictionary etc and some useful feature like
capitalization as found in English cannot be found in Assamese. Apart from this we also describe some of
the issues faced in Assamese while doing Named Entity Recognition.
Survey on Indian CLIR and MT systems in Marathi LanguageEditor IJCATR
Cross Language Information Retrieval (CLIR) deals with retrieving relevant information stored in a language different from
the language of user’s query. This helps users to express the information need in their native languages. Machine translation based (MTbased)
approach of CLIR uses existing machine translation techniques to provide automatic translation of queries. This paper covers the
research work done in CLIR and MT systems for Marathi language in India.
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.
A survey on phrase structure learning methods for text classificationijnlc
Text classification is a task of automatic classification of text into one of the predefined categories. The
problem of text classification has been widely studied in different communities like natural language
processing, data mining and information retrieval. Text classification is an important constituent in many
information management tasks like topic identification, spam filtering, email routing, language
identification, genre classification, readability assessment etc. The performance of text classification
improves notably when phrase patterns are used. The use of phrase patterns helps in capturing non-local
behaviours and thus helps in the improvement of text classification task. Phrase structure extraction is the
first step to continue with the phrase pattern identification. In this survey, detailed study of phrase structure
learning methods have been carried out. This will enable future work in several NLP tasks, which uses
syntactic information from phrase structure like grammar checkers, question answering, information
extraction, machine translation, text classification. The paper also provides different levels of classification
and detailed comparison of the phrase structure learning methods.
SYLLABLE-BASED NEURAL NAMED ENTITY RECOGNITION FOR MYANMAR LANGUAGEijnlc
Named Entity Recognition (NER) for Myanmar Language is essential to Myanmar natural language processing research work. In this work, NER for Myanmar language is treated as a sequence tagging problem and the effectiveness of deep neural networks on NER for Myanmar language has been investigated. Experiments are performed by applying deep neural network architectures on syllable level Myanmar contexts. Very first manually annotated NER corpus for Myanmar language is also constructed and proposed. In developing our in-house NER corpus, sentences from online news website and also sentences supported from ALT-Parallel-Corpus are also used. This ALT corpus is one part of the Asian Language Treebank (ALT) project under ASEAN IVO. This paper contributes the first evaluation of neural network models on NER task for Myanmar language. The experimental results show that those neural sequence models can produce promising results compared to the baseline CRF model. Among those neural architectures, bidirectional LSTM network added CRF layer above gives the highest F-score value. This work also aims to discover the effectiveness of neural network approaches to Myanmar textual processing as well as to promote further researches on this understudied language.
Part of Speech tagging in Indian Languages is still an open problem. We still lack a clear approach in implementing a POS tagger for Indian Languages. In this paper we describe our efforts to build a Hidden Markov Model based Part of Speech Tagger. We have used IL POS tag set for the development of this tagger. We have achieved the accuracy of 92%
Design and Development of a Malayalam to English Translator- A Transfer Based...Waqas Tariq
This paper describes a transfer based scheme for translating Malayalam, a Dravidian language, to English. This system inputs Malayalam sentences and outputs equivalent English sentences. The system comprises of a preprocessor for splitting the compound words, a morphological parser for context disambiguation and chunking, a syntactic structure transfer module and a bilingual dictionary. All the modules are morpheme based to reduce dictionary size. The system does not rely on a stochastic approach and it is based on a rule-based architecture along with various linguistic knowledge components of both Malayalam and English. The system uses two sets of rules: rules for Malayalam morphology and rules for syntactic structure transfer from Malayalam to English. The system is designed using artificial intelligence techniques.
Automatic classification of bengali sentences based on sense definitions pres...ijctcm
Based on the sense definition of words available in the Bengali WordNet, an attempt is made to classify the
Bengali sentences automatically into different groups in accordance with their underlying senses. The input
sentences are collected from 50 different categories of the Bengali text corpus developed in the TDIL
project of the Govt. of India, while information about the different senses of particular ambiguous lexical
item is collected from Bengali WordNet. In an experimental basis we have used Naive Bayes probabilistic
model as a useful classifier of sentences. We have applied the algorithm over 1747 sentences that contain a
particular Bengali lexical item which, because of its ambiguous nature, is able to trigger different senses
that render sentences in different meanings. In our experiment we have achieved around 84% accurate
result on the sense classification over the total input sentences. We have analyzed those residual sentences
that did not comply with our experiment and did affect the results to note that in many cases, wrong
syntactic structures and less semantic information are the main hurdles in semantic classification of
sentences. The applicational relevance of this study is attested in automatic text classification, machine
learning, information extraction, and word sense disambiguation
ON THE UTILITY OF A SYLLABLE-LIKE SEGMENTATION FOR LEARNING A TRANSLITERATION...cscpconf
Source and target word segmentation and alignment is a primary step in the statistical learning of a Transliteration. Here, we analyze the benefit of a syllable-like segmentation approach for learning a transliteration from English to an Indic language, which aligns the training set word pairs in terms of sub-syllable-like units instead of individual character units. While this has been found useful in the case of dealing with Out-of-vocabulary words in English-Chinese in the presence of multiple target dialects, we asked if this would be true for Indic languages which are simpler in their phonetic representation and pronunciation. We expected this syllable-like method to perform marginally better, but we found instead that even though our proposed approach improved the Top-1 accuracy, the individual-character-unit alignment model
somewhat outperformed our approach when the Top-10 results of the system were re-ranked using language modeling approaches. Our experiments were conducted for English to Telugu transliteration (our method will apply equally well to most written Indic languages); our training consisted of a syllable-like segmentation and alignment of a large training set, on which we built a statistical model by modifying a previous character-level maximum entropy based Transliteration learning system due to Kumaran and Kellner; our testing consisted of using the same segmentation of a test English word, followed by applying the model, and reranking the resulting top 10 Telugu words. We also report the dataset creation and selection since standard datasets are not available.
Named Entity Recognition using Hidden Markov Model (HMM)kevig
Named Entity Recognition (NER) is the subtask of Natural Language Processing (NLP) which is the branch of artificial intelligence. It has many applications mainly in machine translation, text to speech synthesis, natural language understanding, Information Extraction, Information retrieval, question answering etc. The aim of NER is to classify words into some predefined categories like location name, person name, organization name, date, time etc. In this paper we describe the Hidden Markov Model (HMM) based approach of machine learning in detail to identify the named entities. The main idea behind the use of HMM model for building NER system is that it is language independent and we can apply this system for any language domain. In our NER system the states are not fixed means it is of dynamic in nature one can use it according to their interest. The corpus used by our NER system is also not domain specific
Comparative performance analysis of two anaphora resolution systemsijfcstjournal
Anaphora Resolution is the process of finding referents in the given discourse. Anaphora Resolution is one
of the complex tasks of linguistics. This paper presents the performance analysis of two computational
models that uses Gazetteer method for resolving anaphora in Hindi Language. In Gazetteer method
different classes (Gazettes) of elements are created. These Gazettes are used to provide external knowledge
to the system. The two models use Recency and Animistic factor for resolving anaphors. For Recency factor
first model uses the concept of centering approach and second uses the concept of Lappin Leass approach.
Gazetteers are used to provide Animistic knowledge. This paper presents the experimental results of both
the models. These experiments are conducted on short Hindi stories, news articles and biography content
from Wikipedia. The respective accuracy for both the model is analyzed and finally the conclusion is drawn
for the best suitable model for Hindi Language.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Abstract This paper represents a Semantic Analyzer for checking the semantic correctness of the given input text. We describe our system as the one which analyzes the text by comparing it with the meaning of the words given in the WordNet. The Semantic Analyzer thus developed not only detects and displays semantic errors in the text but it also corrects them. Keywords: Part of Speech (POS) Tagger, Morphological Analyzer, Syntactic Analyzer, Semantic Analyzer, Natural Language (NL)
A template based algorithm for automatic summarization and dialogue managemen...eSAT Journals
Abstract This paper describes an automated approach for extracting significant and useful events from unstructured text. The goal of research is to come out with a methodology which helps in extracting important events such as dates, places, and subjects of interest. It would be also convenient if the methodology helps in presenting the users with a shorter version of the text which contain all non-trivial information. We also discuss implementation of algorithms which exactly does this task, developed by us. Key Words: Cosine Similarity, Information, Natural Language, Summarization, Text Mining
Rule-based Prosody Calculation for Marathi Text-to-Speech SynthesisIJERA Editor
This research paper presents two empirical studies that examine the influence of different linguistic aspects on
prosody in Marathi. First, we analyzed a Marathi corpus with respect to the effect of syntax and information
status on prosody. Second, we conducted a listening test which investigated the prosodic realisation of
constituents in the Marathi depending on their information status. The results were used to improve the prosody
prediction in the Marathi text-to-speech synthesis system MARY.
Taxonomy extraction from automotive natural language requirements using unsup...ijnlc
In this paper we present a novel approach to semi-automatically learn concept hierarchies from natural
language requirements of the automotive industry. The approach is based on the distributional hypothesis
and the special characteristics of domain-specific German compounds. We extract taxonomies by using
clustering techniques in combination with general thesauri. Such a taxonomy can be used to support
requirements engineering in early stages by providing a common system understanding and an agreedupon
terminology. This work is part of an ontology-driven requirements engineering process, which builds
on top of the taxonomy. Evaluation shows that this taxonomy extraction approach outperforms common
hierarchical clustering techniques.
A Context-based Numeral Reading Technique for Text to Speech Systems IJECEIAES
This paper presents a novel technique for context based numeral reading in Indian language text to speech systems. The model uses a set of rules to determine the context of the numeral pronunciation and is being integrated with the waveform concatenation technique to produce speech out of the input text in Indian languages. For this purpose, the three Indian languages Odia, Hindi and Bengali are considered. To analyze the performance of the proposed technique, a set of experiments are performed considering different context of numeral pronunciations and the results are compared with existing syllable-based technique. The results obtained from different experiments shows the effectiveness of the proposed technique in producing intelligible speech out of the entered text utterances compared to the existing technique even with very less storage and execution time.
A legal text usually long and complicated, it has some characteristic that make it different from other dailyuse
texts.Then, translating a legal text is generally considered to be difficult. This paper introduces an approach to split a legal sentence based on its logical structure and presents selecting appropriate
translation rules to improve phrase reordering of legal translation. We use a method which divides a English legal sentence based on its logical structure to segment the legal sentence. New features with rich linguistic and contextual information of split sentences are proposed to rule selection. We apply maximum entropy to combine rich linguistic and contextual information and integrate the features of split sentences into the legal translation, tree-based SMT system. We obtain improvements in performance for legal translation from English to Japanese over Moses and Moses-chart systems.
Trusted Advisor
We bring our IT skills and knowledge to support infrastructure aimed at business processes efficiency and energy savings.
Our experience in physical infrastructure, wireless, data center, networking and security technologies and the long-term partnerships with the best of breed market leaders allow us to deliver value added services for the control, management and optimization of customer applications and processes.
A survey on phrase structure learning methods for text classificationijnlc
Text classification is a task of automatic classification of text into one of the predefined categories. The
problem of text classification has been widely studied in different communities like natural language
processing, data mining and information retrieval. Text classification is an important constituent in many
information management tasks like topic identification, spam filtering, email routing, language
identification, genre classification, readability assessment etc. The performance of text classification
improves notably when phrase patterns are used. The use of phrase patterns helps in capturing non-local
behaviours and thus helps in the improvement of text classification task. Phrase structure extraction is the
first step to continue with the phrase pattern identification. In this survey, detailed study of phrase structure
learning methods have been carried out. This will enable future work in several NLP tasks, which uses
syntactic information from phrase structure like grammar checkers, question answering, information
extraction, machine translation, text classification. The paper also provides different levels of classification
and detailed comparison of the phrase structure learning methods.
SYLLABLE-BASED NEURAL NAMED ENTITY RECOGNITION FOR MYANMAR LANGUAGEijnlc
Named Entity Recognition (NER) for Myanmar Language is essential to Myanmar natural language processing research work. In this work, NER for Myanmar language is treated as a sequence tagging problem and the effectiveness of deep neural networks on NER for Myanmar language has been investigated. Experiments are performed by applying deep neural network architectures on syllable level Myanmar contexts. Very first manually annotated NER corpus for Myanmar language is also constructed and proposed. In developing our in-house NER corpus, sentences from online news website and also sentences supported from ALT-Parallel-Corpus are also used. This ALT corpus is one part of the Asian Language Treebank (ALT) project under ASEAN IVO. This paper contributes the first evaluation of neural network models on NER task for Myanmar language. The experimental results show that those neural sequence models can produce promising results compared to the baseline CRF model. Among those neural architectures, bidirectional LSTM network added CRF layer above gives the highest F-score value. This work also aims to discover the effectiveness of neural network approaches to Myanmar textual processing as well as to promote further researches on this understudied language.
Part of Speech tagging in Indian Languages is still an open problem. We still lack a clear approach in implementing a POS tagger for Indian Languages. In this paper we describe our efforts to build a Hidden Markov Model based Part of Speech Tagger. We have used IL POS tag set for the development of this tagger. We have achieved the accuracy of 92%
Design and Development of a Malayalam to English Translator- A Transfer Based...Waqas Tariq
This paper describes a transfer based scheme for translating Malayalam, a Dravidian language, to English. This system inputs Malayalam sentences and outputs equivalent English sentences. The system comprises of a preprocessor for splitting the compound words, a morphological parser for context disambiguation and chunking, a syntactic structure transfer module and a bilingual dictionary. All the modules are morpheme based to reduce dictionary size. The system does not rely on a stochastic approach and it is based on a rule-based architecture along with various linguistic knowledge components of both Malayalam and English. The system uses two sets of rules: rules for Malayalam morphology and rules for syntactic structure transfer from Malayalam to English. The system is designed using artificial intelligence techniques.
Automatic classification of bengali sentences based on sense definitions pres...ijctcm
Based on the sense definition of words available in the Bengali WordNet, an attempt is made to classify the
Bengali sentences automatically into different groups in accordance with their underlying senses. The input
sentences are collected from 50 different categories of the Bengali text corpus developed in the TDIL
project of the Govt. of India, while information about the different senses of particular ambiguous lexical
item is collected from Bengali WordNet. In an experimental basis we have used Naive Bayes probabilistic
model as a useful classifier of sentences. We have applied the algorithm over 1747 sentences that contain a
particular Bengali lexical item which, because of its ambiguous nature, is able to trigger different senses
that render sentences in different meanings. In our experiment we have achieved around 84% accurate
result on the sense classification over the total input sentences. We have analyzed those residual sentences
that did not comply with our experiment and did affect the results to note that in many cases, wrong
syntactic structures and less semantic information are the main hurdles in semantic classification of
sentences. The applicational relevance of this study is attested in automatic text classification, machine
learning, information extraction, and word sense disambiguation
ON THE UTILITY OF A SYLLABLE-LIKE SEGMENTATION FOR LEARNING A TRANSLITERATION...cscpconf
Source and target word segmentation and alignment is a primary step in the statistical learning of a Transliteration. Here, we analyze the benefit of a syllable-like segmentation approach for learning a transliteration from English to an Indic language, which aligns the training set word pairs in terms of sub-syllable-like units instead of individual character units. While this has been found useful in the case of dealing with Out-of-vocabulary words in English-Chinese in the presence of multiple target dialects, we asked if this would be true for Indic languages which are simpler in their phonetic representation and pronunciation. We expected this syllable-like method to perform marginally better, but we found instead that even though our proposed approach improved the Top-1 accuracy, the individual-character-unit alignment model
somewhat outperformed our approach when the Top-10 results of the system were re-ranked using language modeling approaches. Our experiments were conducted for English to Telugu transliteration (our method will apply equally well to most written Indic languages); our training consisted of a syllable-like segmentation and alignment of a large training set, on which we built a statistical model by modifying a previous character-level maximum entropy based Transliteration learning system due to Kumaran and Kellner; our testing consisted of using the same segmentation of a test English word, followed by applying the model, and reranking the resulting top 10 Telugu words. We also report the dataset creation and selection since standard datasets are not available.
Named Entity Recognition using Hidden Markov Model (HMM)kevig
Named Entity Recognition (NER) is the subtask of Natural Language Processing (NLP) which is the branch of artificial intelligence. It has many applications mainly in machine translation, text to speech synthesis, natural language understanding, Information Extraction, Information retrieval, question answering etc. The aim of NER is to classify words into some predefined categories like location name, person name, organization name, date, time etc. In this paper we describe the Hidden Markov Model (HMM) based approach of machine learning in detail to identify the named entities. The main idea behind the use of HMM model for building NER system is that it is language independent and we can apply this system for any language domain. In our NER system the states are not fixed means it is of dynamic in nature one can use it according to their interest. The corpus used by our NER system is also not domain specific
Comparative performance analysis of two anaphora resolution systemsijfcstjournal
Anaphora Resolution is the process of finding referents in the given discourse. Anaphora Resolution is one
of the complex tasks of linguistics. This paper presents the performance analysis of two computational
models that uses Gazetteer method for resolving anaphora in Hindi Language. In Gazetteer method
different classes (Gazettes) of elements are created. These Gazettes are used to provide external knowledge
to the system. The two models use Recency and Animistic factor for resolving anaphors. For Recency factor
first model uses the concept of centering approach and second uses the concept of Lappin Leass approach.
Gazetteers are used to provide Animistic knowledge. This paper presents the experimental results of both
the models. These experiments are conducted on short Hindi stories, news articles and biography content
from Wikipedia. The respective accuracy for both the model is analyzed and finally the conclusion is drawn
for the best suitable model for Hindi Language.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Abstract This paper represents a Semantic Analyzer for checking the semantic correctness of the given input text. We describe our system as the one which analyzes the text by comparing it with the meaning of the words given in the WordNet. The Semantic Analyzer thus developed not only detects and displays semantic errors in the text but it also corrects them. Keywords: Part of Speech (POS) Tagger, Morphological Analyzer, Syntactic Analyzer, Semantic Analyzer, Natural Language (NL)
A template based algorithm for automatic summarization and dialogue managemen...eSAT Journals
Abstract This paper describes an automated approach for extracting significant and useful events from unstructured text. The goal of research is to come out with a methodology which helps in extracting important events such as dates, places, and subjects of interest. It would be also convenient if the methodology helps in presenting the users with a shorter version of the text which contain all non-trivial information. We also discuss implementation of algorithms which exactly does this task, developed by us. Key Words: Cosine Similarity, Information, Natural Language, Summarization, Text Mining
Rule-based Prosody Calculation for Marathi Text-to-Speech SynthesisIJERA Editor
This research paper presents two empirical studies that examine the influence of different linguistic aspects on
prosody in Marathi. First, we analyzed a Marathi corpus with respect to the effect of syntax and information
status on prosody. Second, we conducted a listening test which investigated the prosodic realisation of
constituents in the Marathi depending on their information status. The results were used to improve the prosody
prediction in the Marathi text-to-speech synthesis system MARY.
Taxonomy extraction from automotive natural language requirements using unsup...ijnlc
In this paper we present a novel approach to semi-automatically learn concept hierarchies from natural
language requirements of the automotive industry. The approach is based on the distributional hypothesis
and the special characteristics of domain-specific German compounds. We extract taxonomies by using
clustering techniques in combination with general thesauri. Such a taxonomy can be used to support
requirements engineering in early stages by providing a common system understanding and an agreedupon
terminology. This work is part of an ontology-driven requirements engineering process, which builds
on top of the taxonomy. Evaluation shows that this taxonomy extraction approach outperforms common
hierarchical clustering techniques.
A Context-based Numeral Reading Technique for Text to Speech Systems IJECEIAES
This paper presents a novel technique for context based numeral reading in Indian language text to speech systems. The model uses a set of rules to determine the context of the numeral pronunciation and is being integrated with the waveform concatenation technique to produce speech out of the input text in Indian languages. For this purpose, the three Indian languages Odia, Hindi and Bengali are considered. To analyze the performance of the proposed technique, a set of experiments are performed considering different context of numeral pronunciations and the results are compared with existing syllable-based technique. The results obtained from different experiments shows the effectiveness of the proposed technique in producing intelligible speech out of the entered text utterances compared to the existing technique even with very less storage and execution time.
A legal text usually long and complicated, it has some characteristic that make it different from other dailyuse
texts.Then, translating a legal text is generally considered to be difficult. This paper introduces an approach to split a legal sentence based on its logical structure and presents selecting appropriate
translation rules to improve phrase reordering of legal translation. We use a method which divides a English legal sentence based on its logical structure to segment the legal sentence. New features with rich linguistic and contextual information of split sentences are proposed to rule selection. We apply maximum entropy to combine rich linguistic and contextual information and integrate the features of split sentences into the legal translation, tree-based SMT system. We obtain improvements in performance for legal translation from English to Japanese over Moses and Moses-chart systems.
Trusted Advisor
We bring our IT skills and knowledge to support infrastructure aimed at business processes efficiency and energy savings.
Our experience in physical infrastructure, wireless, data center, networking and security technologies and the long-term partnerships with the best of breed market leaders allow us to deliver value added services for the control, management and optimization of customer applications and processes.
Automatic convey or System with In–Process Sorting Mechanism using PLC and HM...IJERA Editor
Programmable logic controllers are widely used in many manufacturing process like machinery packaging
material handling automatic assembly. These are special type of microprocessor based controller used for any
application that needs any kind of electrical controller including lighting controller and HVAC control system.
Automatic conveyor system is a computerized control method of controlling and managing the sorting
mechanism at the same time maintaining the efficiency of the industry & quality of the products.HMI for
automatic conveyor system is considered the primary way of controlling each operation. Text displays are
available as well as graphical touch screens. It is used in touch panels and local monitoring of machines. This
paper deals with the efficient use of PLC in automatic conveyor system and also building the accuracy in it.
Emotional telugu speech signals classification based on k nn classifiereSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology.
Emotional telugu speech signals classification based on k nn classifiereSAT Journals
Abstract Speech processing is the study of speech signals, and the methods used to process them. In application such as speech coding, speech synthesis, speech recognition and speaker recognition technology, speech processing is employed. In speech classification, the computation of prosody effects from speech signals plays a major role. In emotional speech signals pitch and frequency is a most important parameters. Normally, the pitch value of sad and happy speech signals has a great difference and the frequency value of happy is higher than sad speech. But, in some cases the frequency of happy speech is nearly similar to sad speech or frequency of sad speech is similar to happy speech. In such situation, it is difficult to recognize the exact speech signal. To reduce such drawbacks, in this paper we propose a Telugu speech emotion classification system with three features like Energy Entropy, Short Time Energy, Zero Crossing Rate and K-NN classifier for the classification. Features are extracted from the speech signals and given to the K-NN. The implementation result shows the effectiveness of proposed speech emotion classification system in classifying the Telugu speech signals based on their prosody effects. The performance of the proposed speech emotion classification system is evaluated by conducting cross validation on the Telugu speech database. Keywords: Emotion Classification, K-NN classifier, Energy Entropy, Short Time Energy, Zero Crossing Rate.
SIMILAR THESAURUS BASED ON ARABIC DOCUMENT: AN OVERVIEW AND COMPARISONIJCSEA Journal
The massive grow of the modern information retrieval system (IRS), especially in natural languages
becomes more difficult. The search in Arabic languages, as natural language, is not good enough yet. This
paper will try to build similar thesaurus based on Arabic language in two mechanisms, the first one is full
word mechanisms and the other is stemmed mechanisms, and then to compare between them.
The comparison made by this study proves that the similar thesaurus using stemmed mechanisms get more
better results than using traditional in the same mechanisms and similar thesaurus improved more the
recall and precision than traditional information retrieval system at recall and precision levels.
A COMPREHENSIVE ANALYSIS OF STEMMERS AVAILABLE FOR INDIC LANGUAGES ijnlc
Stemming is the process of term conflation. It conflates all the word variants to a common form called as stem. It plays significant role in numerous Natural Language Processing (NLP) applications like morphological analysis, parsing, document summarization, text classification, part-of-speech tagging, question-answering system, machine translation, word sense disambiguation, information retrieval (IR), etc. Each of these tasks requires some pre-processing to be done. Stemming is one of the important building blocks for all these applications. This paper, presents an overview of various stemming techniques, evaluation criteria for stemmers and various existing stemmers for Indic languages.
A COMPARATIVE STUDY OF FEATURE SELECTION METHODSkevig
This article focuses on evaluating and comparing the available feature selection methods in general versatility regarding authorship attribution problems and tries to identify which method is the most effective. The discussions on general versatility of feature selection methods and its connection in selecting the appropriate features for varying data were done. In addition, different languages, different types of features, different systems for calculating the accuracy of SVM (support vector machine), and different criteria for determining the rank of feature selection methods were used to measure the general versatility of these methods together. The analysis results indicate the best feature selection method is different for each dataset; however, some methods can always extract useful information to discriminate the classes. The chi-square was proved to be a better method overall.
Improving a Lightweight Stemmer for Gujarati Languageijistjournal
The origin of route of text mining is the process of stemming. It is usually used in several types of applications such as Natural Language Processing (NLP), Information Retrieval (IR) and Text Mining (TM) including Text Categorization (TC), Text Summarization (TS). Establish a stemmer effective for the language of Gujarati has been always a search domain hot since the Gujarati has a very different structure and difficult that the other language due to the rich morphology.
SYLLABLE-BASED NEURAL NAMED ENTITY RECOGNITION FOR MYANMAR LANGUAGEkevig
This paper contributes the first evaluation of neural
network models on NER task for Myanmar language. The experimental results show that those neural
sequence models can produce promising results compared to the baseline CRF model. Among those neural
architectures, bidirectional LSTM network added CRF layer above gives the highest F-score value. This
work also aims to discover the effectiveness of neural network approaches to Myanmar textual processing
as well as to promote further researches on this understudied language.
A COMPARATIVE STUDY OF FEATURE SELECTION METHODSkevig
Text analysis has been attracting increasing attention in this data era. Selecting effective features from
datasets is a particular important part in text classification studies. Feature selection excludes irrelevant
features from the classification task, reduces the dimensionality of a dataset, and improves the accuracy
and performance of identification. So far, so many feature selection methods have been proposed, however,
it remains unclear which method is the most effective in practice. This article focuses on evaluating and
comparing the available feature selection methods in general versatility regarding authorship attribution
problems and tries to identify which method is the most effective. The discussions on general versatility of
feature selection methods and its connection in selecting the appropriate features for varying data were
done. In addition, different languages, different types of features, different systems for calculating the
accuracy of SVM (support vector machine), and different criteria for determining the rank of feature
selection methods were used to measure the general versatility of these methods together. The analysis
results indicate the best feature selection method is different for each dataset; however, some methods can
always extract useful information to discriminate the classes. The chi-square was proved to be a better
method overall.
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.
Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Le...ijtsrd
Natural Language Processing NLP is the one of the major filed of Natural Language Generation NLG . NLG can generate natural language from a machine representation. Generating suggestions for a sentence especially for Indian languages is much difficult. One of the major reason is that it is morphologically rich and the format is just reverse of English language. By using deep learning approach with the help of Long Short Term Memory LSTM layers we can generate a possible set of solutions for erroneous part in a sentence. To effectively generate a bunch of sentences having equivalent meaning as the original sentence using Deep Learning DL approach is to train a model on this task, e.g. we need thousands of examples of inputs and outputs with which to train a model. Veena S Nair | Amina Beevi A ""Suggestion Generation for Specific Erroneous Part in a Sentence using Deep Learning"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-3 | Issue-4 , June 2019, URL: https://www.ijtsrd.com/papers/ijtsrd23842.pdf
Paper URL: https://www.ijtsrd.com/engineering/computer-engineering/23842/suggestion-generation-for-specific-erroneous-part-in-a-sentence-using-deep-learning/veena-s-nair
A COMPARATIVE STUDY OF FEATURE SELECTION METHODSijnlc
Text analysis has been attracting increasing attention in this data era. Selecting effective features from datasets is a particular important part in text classification studies. Feature selection excludes irrelevant features from the classification task, reduces the dimensionality of a dataset, and improves the accuracy and performance of identification. So far, so many feature selection methods have been proposed, however,
it remains unclear which method is the most effective in practice. This article focuses on evaluating and comparing the available feature selection methods in general versatility regarding authorship attribution problems and tries to identify which method is the most effective. The discussions on general versatility of feature selection methods and its connection in selecting the appropriate features for varying data were
done. In addition, different languages, different types of features, different systems for calculating the accuracy of SVM (support vector machine), and different criteria for determining the rank of feature selection methods were used to measure the general versatility of these methods together. The analysis
results indicate the best feature selection method is different for each dataset; however, some methods can always extract useful information to discriminate the classes. The chi-square was proved to be a better method overall.
A hybrid composite features based sentence level sentiment analyzerIAESIJAI
Current lexica and machine learning based sentiment analysis approaches
still suffer from a two-fold limitation. First, manual lexicon construction and
machine training is time consuming and error-prone. Second, the
prediction’s accuracy entails sentences and their corresponding training text
should fall under the same domain. In this article, we experimentally
evaluate four sentiment classifiers, namely support vector machines (SVMs),
Naive Bayes (NB), logistic regression (LR) and random forest (RF). We
quantify the quality of each of these models using three real-world datasets
that comprise 50,000 movie reviews, 10,662 sentences, and 300 generic
movie reviews. Specifically, we study the impact of a variety of natural
language processing (NLP) pipelines on the quality of the predicted
sentiment orientations. Additionally, we measure the impact of incorporating
lexical semantic knowledge captured by WordNet on expanding original
words in sentences. Findings demonstrate that the utilizing different NLP
pipelines and semantic relationships impacts the quality of the sentiment
analyzers. In particular, results indicate that coupling lemmatization and
knowledge-based n-gram features proved to produce higher accuracy results.
With this coupling, the accuracy of the SVM classifier has improved to
90.43%, while it was 86.83%, 90.11%, 86.20%, respectively using the three
other classifiers.
Named Entity Recognition for Telugu Using Conditional Random FieldWaqas Tariq
Named Entity (NE) recognition is a task in which proper nouns and numerical information are extracted from documents and are classified into predefined categories such as Person names, Organization names , Location names, miscellaneous(Date and others). It is a key technology of Information Extraction, Question Answering system, Machine Translations, Information Retrial etc. This paper reports about the development of a NER system for Telugu using Conditional Random field (CRF). Though this state of the art machine learning technique has been widely applied to NER in several well-studied languages, the use of this technique to Telugu languages is very new. The system makes use of the different contextual information of the words along with the variety of features that are helpful in predicting the four different named entities (NE) classes, such as Person name, Location name, Organization name, miscellaneous (Date and others). Keywords: Named entity, Conditional Random field, NE, CRF, NER, named entity recognition
SENTIMENT ANALYSIS IN MYANMAR LANGUAGE USING CONVOLUTIONAL LSTM NEURAL NETWORKijnlc
In recent years, there has been an increasing use of social media among people in Myanmar and writing review on social media pages about the product, movie, and trip are also popular among people. Moreover, most of the people are going to find the review pages about the product they want to buy before deciding whether they should buy it or not. Extracting and receiving useful reviews over interesting products is very important and time consuming for people. Sentiment analysis is one of the important processes for extracting useful reviews of the products. In this paper, the Convolutional LSTM neural network architecture is proposed to analyse the sentiment classification of cosmetic reviews written in Myanmar Language. The paper also intends to build the cosmetic reviews dataset for deep learning and sentiment lexicon in Myanmar Language.
Sentiment Analysis In Myanmar Language Using Convolutional Lstm Neural Networkkevig
In recent years, there has been an increasing use of social media among people in Myanmar and writing
review on social media pages about the product, movie, and trip are also popular among people. Moreover,
most of the people are going to find the review pages about the product they want to buy before deciding
whether they should buy it or not. Extracting and receiving useful reviews over interesting products is very
important and time consuming for people. Sentiment analysis is one of the important processes for extracting
useful reviews of the products. In this paper, the Convolutional LSTM neural network architecture is
proposed to analyse the sentiment classification of cosmetic reviews written in Myanmar Language. The
paper also intends to build the cosmetic reviews dataset for deep learning and sentiment lexicon in Myanmar
Language.
PARSING OF MYANMAR SENTENCES WITH FUNCTION TAGGINGkevig
This paper describes the use of Naive Bayes to address the task of assigning function tags and context free
grammar (CFG) to parse Myanmar sentences. Part of the challenge of statistical function tagging for
Myanmar sentences comes from the fact that Myanmar has free-phrase-order and a complex
morphological system. Function tagging is a pre-processing step for parsing. In the task of function
tagging, we use the functional annotated corpus and tag Myanmar sentences with correct segmentation,
POS (part-of-speech) tagging and chunking information. We propose Myanmar grammar rules and apply
context free grammar (CFG) to find out the parse tree of function tagged Myanmar sentences. Experiments
show that our analysis achieves a good result with parsing of simple sentences and three types of complex
sentences
Similar to Duration for Classification and Regression Treefor Marathi Textto- Speech Synthesis System (20)
Forklift Classes Overview by Intella PartsIntella Parts
Discover the different forklift classes and their specific applications. Learn how to choose the right forklift for your needs to ensure safety, efficiency, and compliance in your operations.
For more technical information, visit our website https://intellaparts.com
Courier management system project report.pdfKamal Acharya
It is now-a-days very important for the people to send or receive articles like imported furniture, electronic items, gifts, business goods and the like. People depend vastly on different transport systems which mostly use the manual way of receiving and delivering the articles. There is no way to track the articles till they are received and there is no way to let the customer know what happened in transit, once he booked some articles. In such a situation, we need a system which completely computerizes the cargo activities including time to time tracking of the articles sent. This need is fulfilled by Courier Management System software which is online software for the cargo management people that enables them to receive the goods from a source and send them to a required destination and track their status from time to time.
TECHNICAL TRAINING MANUAL GENERAL FAMILIARIZATION COURSEDuvanRamosGarzon1
AIRCRAFT GENERAL
The Single Aisle is the most advanced family aircraft in service today, with fly-by-wire flight controls.
The A318, A319, A320 and A321 are twin-engine subsonic medium range aircraft.
The family offers a choice of engines
Immunizing Image Classifiers Against Localized Adversary Attacksgerogepatton
This paper addresses the vulnerability of deep learning models, particularly convolutional neural networks
(CNN)s, to adversarial attacks and presents a proactive training technique designed to counter them. We
introduce a novel volumization algorithm, which transforms 2D images into 3D volumetric representations.
When combined with 3D convolution and deep curriculum learning optimization (CLO), itsignificantly improves
the immunity of models against localized universal attacks by up to 40%. We evaluate our proposed approach
using contemporary CNN architectures and the modified Canadian Institute for Advanced Research (CIFAR-10
and CIFAR-100) and ImageNet Large Scale Visual Recognition Challenge (ILSVRC12) datasets, showcasing
accuracy improvements over previous techniques. The results indicate that the combination of the volumetric
input and curriculum learning holds significant promise for mitigating adversarial attacks without necessitating
adversary training.
About
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Technical Specifications
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
Key Features
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface
• Compatible with MAFI CCR system
• Copatiable with IDM8000 CCR
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
Application
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
Event Management System Vb Net Project Report.pdfKamal Acharya
In present era, the scopes of information technology growing with a very fast .We do not see any are untouched from this industry. The scope of information technology has become wider includes: Business and industry. Household Business, Communication, Education, Entertainment, Science, Medicine, Engineering, Distance Learning, Weather Forecasting. Carrier Searching and so on.
My project named “Event Management System” is software that store and maintained all events coordinated in college. It also helpful to print related reports. My project will help to record the events coordinated by faculties with their Name, Event subject, date & details in an efficient & effective ways.
In my system we have to make a system by which a user can record all events coordinated by a particular faculty. In our proposed system some more featured are added which differs it from the existing system such as security.
Hybrid optimization of pumped hydro system and solar- Engr. Abdul-Azeez.pdffxintegritypublishin
Advancements in technology unveil a myriad of electrical and electronic breakthroughs geared towards efficiently harnessing limited resources to meet human energy demands. The optimization of hybrid solar PV panels and pumped hydro energy supply systems plays a pivotal role in utilizing natural resources effectively. This initiative not only benefits humanity but also fosters environmental sustainability. The study investigated the design optimization of these hybrid systems, focusing on understanding solar radiation patterns, identifying geographical influences on solar radiation, formulating a mathematical model for system optimization, and determining the optimal configuration of PV panels and pumped hydro storage. Through a comparative analysis approach and eight weeks of data collection, the study addressed key research questions related to solar radiation patterns and optimal system design. The findings highlighted regions with heightened solar radiation levels, showcasing substantial potential for power generation and emphasizing the system's efficiency. Optimizing system design significantly boosted power generation, promoted renewable energy utilization, and enhanced energy storage capacity. The study underscored the benefits of optimizing hybrid solar PV panels and pumped hydro energy supply systems for sustainable energy usage. Optimizing the design of solar PV panels and pumped hydro energy supply systems as examined across diverse climatic conditions in a developing country, not only enhances power generation but also improves the integration of renewable energy sources and boosts energy storage capacities, particularly beneficial for less economically prosperous regions. Additionally, the study provides valuable insights for advancing energy research in economically viable areas. Recommendations included conducting site-specific assessments, utilizing advanced modeling tools, implementing regular maintenance protocols, and enhancing communication among system components.
Water scarcity is the lack of fresh water resources to meet the standard water demand. There are two type of water scarcity. One is physical. The other is economic water scarcity.
Duration for Classification and Regression Treefor Marathi Textto- Speech Synthesis System
1. Sangramsing Kayte Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 5, Issue 11, (Part - 4) November 2015, pp.115-119
www.ijera.com 115 | P a g e
Duration for Classification and Regression Treefor Marathi Text-
to-Speech Synthesis System
Sangramsing N. Kayte1
, Monica Mundada1
,Dr. Charansing N. Kayte
2
, Dr.
Bharti Gawali*
1,3
Department of Computer Science and Information Technology Dr. Babasaheb Ambedkar Marathwada
University, Aurangabad
2
Department of Digital and Cyber Forensic, Aurangabad, Maharashtra
Abstract
This research paper reports preliminary results of data-driven modeling of segmentalphoneme duration for
Marathi. Classification and Regression Tree based data driven duration modeling for segmental duration
prediction is presented. A number of features are considered and their usefulness and relative contribution for
segmental duration prediction is assessed. Objective evaluation of the duration model, by root mean squared
prediction error and correlation between actual and predicted durations, is performed.
I. Introduction
Accurate estimation of segmental durations is
crucial for natural sounding text-to-speech synthesis
[1-2]. Variation in segmental duration serves as a cue
to the identity of a speech sound and helps to segment
a continuous flow of sounds into words and phrases
thereby increasing the naturalness and intelligibility.
The primary goal in duration modeling is to model
the duration pattern of natural speech, considering
various features that affect the pattern. An important
restriction being that, due to the nature of the Text-to-
Speech synthesis problem, i.e., as only text is
provided for the synthesis, only those features that
can be automatically derived from text can be
considered.
The approaches to segmental duration modeling
can be divided into two categories: rule-based and
corpusbased. The most prevalent rule-based duration
model is a sequential rule based system proposed by
Klatt [2], which is implemented in the MI-Talk
classification [3]. In this system, starting fromsome
intrinsic rule, the durationof a segment is modified by
rules that are applied sequentially. Models of this type
have been developed for several languages [4, 5].
However, rule-based models often over-generalize
and cannot handle exceptions well without getting
exceedingly complicated. When large speech corpora
and the computational means for analyzing these
corpora became available, new data-driven
approaches based on Classification and Regression
Trees [6], linear statistical models and Artificial
Neural Networks [7] have been increasingly used for
duration modeling.
In this paper, duration modeling for Marathi is
performed using data-drivenapproachbased on CART.
Classification and Regression Trees are models based
on self-learning procedures that sort the instances in
the learning data by binary questions about the
attributes that the instances have. It starts at the root
node and continues to ask questions about the
attributes of the instance down the tree until a leaf
node is reached [1,2,3,8]. For each node, the decision
tree algorithm selects the best attribute, and also the
question to be asked about that attribute. The
selection is based on what attribute and question
about it divide the learning data so that it gives the
best predictive value for right classification. CART
modeling is particularly useful in the case of less
researched languages like Indian languages, for which
the most relevant features that affect the duration
pattern and the way they are inter-related have not
been studied in detail.
This paper is organized as follows. Section 2
gives the background for the work presented in this
paper. In Section 3, details about the speech corpus
that is used for the duration analysis are presented.
Section 4 describes the features considered for
duration modeling and subsequent generation of
feature vectors from which the CART based duration
model is trained. Section 5 describes the stepwise
construction of CART model for analysis on the
contribution and relative importance of various
features. In Section 6, objective evaluation of the
duration model, by root mean squared prediction error
and correlation between actual and predicted
durations, is presented.
RESEARCH ARTICLE OPEN ACCESS
2. Sangramsing Kayte Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 5, Issue 11, (Part - 4) November 2015, pp.115-119
www.ijera.com 116 | P a g e
II. Marathi TTS System
Marathi is an Indo-Aryan language spoken by about
71 million people mainly in the Indian state of
Maharashtra and neighboring states. Marathi is also
spoken in Israel and Mauritius. Marathi is thought to
be a descendent of Maharashtra, one of the Prakrit
languages which developed from Sanskrit. Marathi
first appeared in writing during the 11th century in
the form of inscriptions on stones and copper plates.
From the 13th century until the mid-20th century, it
was written with the Modi alphabet. Since 1950 it has
been written with the Devanāgarī alphabet[9,10].
The development of a high quality Marathi TTS
system [11] is under progress at HP Labs India. This
effort is a part of the Local Language Speech
Technology Initiative [7,11], which brings together
motivated groups around the world, providing tools,
expertise, support and training to enable TTS to be
developed in local languages. The aim of LLSTI is to
develop a TTS framework around Festival that will
allow for a rapid development of TTS in any
language[8,10,12].
2.1 Devanāgarī alphabet for Marathi
Vowels and vowel diacritics [9]
Consonants [9]
3. Sangramsing Kayte Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 5, Issue 11, (Part - 4) November 2015, pp.115-119
www.ijera.com 117 | P a g e
III. Speech corpus used
The present study of segmental durations in
natural speech is based on a corpus of around 90
minute duration, which consists of 1000 sentences
taken from three short stories. All the sentences are
spoken by a native Marathi male speaker in
expressive story reading style. The speaker is also a
professional radio artist. The recorded data is
manually segmented at phoneme level using
Pratt[13,14], thus yielding a total of 10,000 segments.
The data is divided randomly into training data
(10,000 segments, 85% of the total segments) and test
data (1000 segments, 15% of the total segments). A
total of 68 phonemes are analysed for their context-
dependent durations.
IV. Feature vector generation
Based on the literature [9,10,11,12,13], a number
of features are considered for segmental duration
prediction. Only those features that can be
automatically derived from text are considered. For
example, information about the focus or stress, accent
assignment and word boundary strength are not
considered even though they are known to affect
duration pattern. However, ‟stress‟ in Maharashtra
languages is not as clearly studied (both acoustically
and perceptually) as in a stress language like English.
Each segment in the corpus is annotated with the
following features together with the actual segment
(phoneme) duration:
Segment identity; e.g., /ka/, /ka/, /S/.
Segment features; e.g., vowel length, vowel height,
consonant type, consonant voicing.
Previous segment (immediate left context) features;
e.g., vowel length, vowel height, consonant type,
consonant voicing.
Next segment (immediate right context) features; e.g.,
vowel length, vowel height, consonant type,
consonant voicing.
Parent syllable structure; e.g., onset, coda, onset size,
coda size.
Position in the parent syllable; Position of the
segment in the syllable it is related to. The index
counts from 0.
Parent syllable initial; Returns 1 if the segment is the
first segment in the syllable it is part of, otherwise 0.
Parent syllable final; Returns 1 if the segment is the
last segment in the syllable it is part of, otherwise 0.
Parent syllable position type; the type of syllable
position in the word it is part of. This may be any of:
„single‟ for single syllable words, „initial‟ for word
initial syllables in a poly-syllabic word, „final‟ for
word final syllables in poly-syllabic words, and „mid‟
for syllables within poly-syllabic words. Number of
syllables in the parent word.
Position of the parent syllable; the position of the
syllable in the word it is part of. The index counts
from 0.
Parent syllables break information; Break level after
the parent syllable. This feature is categorical and it
has 4 possible values: 0 for word internal syllables, 1
for syllables occurring in word boundary, 3 for
syllables occurring in phrase boundary, 4 for syllables
occurring in sentence boundary.
Phrase length in number of words.
Position of phrase in the utterance.
Number of phrases in the utterance.
The speech corpus used for modeling and analysis
is currently not optimal for duration modeling, since
we could not take care of to take care of data sparsity
problem or cover feature space. However, to reduce
the problem caused due to a small data set, care has
been taken to represent the feature space in a
generalized manner. For example, the segmental
context immediate left and right context is
represented using various features front vowel,
consonant type. instead of the absolute identities.
V. Generation of CART duration model
Classification and Regression Tree based
duration model is trained with feature data described
in Section 4. Since there is no previous knowledge
about the usefulness of the features and their relative
importance, CART‟s are built in a step-wise fashion
to establish the usefulness and relative importance of
the features. In this approach, each single feature is
taken in turn and a tree consisting of nodes
containing only the conditions imposed by that
feature is built. The single best tree is then kept and
each remaining feature is taken in turn and added to
the tree to find the best tree possible with just two
features. The procedure is then repeated for the third,
fourth, fifth feature and so on. This process continues
until no significant gain in accuracy is obtained by
4. Sangramsing Kayte Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 5, Issue 11, (Part - 4) November 2015, pp.115-119
www.ijera.com 118 | P a g e
adding more features. For running the CART
building process, ‟Wagon‟ classification and
regression tree tool [15,16] is used. Detailed analysis
on the usefulness of the proposed features and their
relative importance is given in Section 6.
5.1. Prediction of segmental duration
The segmental durations are predicted by traversing
the decision tree starting from the root node, taking
various paths satisfying the conditions at intermediate
nodes, till the leaf node is reached. The path taken
depends on various features like, the segment
identity, preceding and following segment identities,
position of the segment in parent syllable and
position of the syllable in parent word. The leaf node
contains the predicted value of segmental duration.
An example partial decision tree for segmental
duration prediction is shown in Figure 1. The tree
assigns different durations for segment /u/ when it
occurs in different contexts. A duration value of 110
ms is assigned when it satisfies the following criteria:
the preceding segment is /th/, parent syllable is the
final syllable in the parent word, and there is a break
(or pause) after the parent syllable. A duration value
of 70 ms is assigned when it satisfies the following
criteria: the preceding segment is /th/, parent syllable
is the final syllable in the parent word, and the parent
syllable is not at the end of a phrase break. A duration
value of 85 ms is assigned when the preceding
segment is /th/ and the following segment is /n/. A
duration value of 65 ms is assigned when the
preceding segment is /p/ and the following segment is
/d/.
VI. Objective evaluation and discussion
Objective evaluation of the duration models, by
root mean squared prediction error (RMSE) and
correlation between actual and predicted durations, is
performed. The duration model is trained with
training data (11282 segments, 90% of the total
segments) and evaluated with test data (1253
segments, 10% of the total segments).
5. Sangramsing Kayte Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 5, Issue 11, (Part - 4) November 2015, pp.115-119
www.ijera.com 119 | P a g e
Figure 1: An example partial decision tree (CART) for segmental duration prediction. The triangles depict
omitted parts.
Correlation obtained between the actual and predicted durations is 0.8997 and RMSE of prediction is 28.82 ms.
To assess the effectiveness of the features considered, CART‟s are built in a step-wise fashion (as described
in Section 5) and the results are shown in Table 1.
Table 1: Analysis on effectiveness of features in calculating segmental time.
Feature used Correlation
Segment Identity 0.6234
Next Segment (onset coda) 0.7112
Next Segment Vowel rounding (1 0) 0.7302
Next Segment Consonant Type 0.7423
Previous Syllable Break 0.7511
Syllable Coda Size 0.7587
Syllable Position (in word) 0.7691
6. Sangramsing Kayte Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 5, Issue 11, (Part - 4) November 2015, pp.115-119
www.ijera.com 120 | P a g e
Previous Segment Consonant Type 0.7744
Previous Segment Vowel Height 0.7869
Syllable Break 0.7987
The first column gives the names of the feature,
and the secondcolumn gives the
correlationobtainedbetween actual and predicted
durations by the addition of the successive features in
the CART modeling process. From the results, we
observe that the most important feature that
contributed to segmental duration prediction is the
identity of the segment itself. Other important
features in decreasing order of importance are:
Next segment‟s syllable structure - whether the
next segment is onset or coda of its parent syllable.
Next segment type - vowel rounding and consonant
type of next segment.
Previous syllable break information.
Parent syllable coda size.
Syllable position in word.
Previous segment type - consonant type and vowel
height of previous segment.
Parent syllable break information.
Though the segmental identity is the most
important feature, the prediction of segmental
duration is improved greatly by additional features
viz. syllable structure, immediate context type (right
and left) and syllable break information.
VII. Conclusions
Earliest results on data-driven Marathi duration
modeling is presented. Classification and Regression
Tree based approach for modeling segmental duration
is followed. A number of features are considered and
their usefulness and relative contribution to
segmental duration prediction is assessed. Work is in
progress on preparing large annotated speech corpora
and better prosody learning.
References
[1.] Monica Mundada, Sangramsing Kayte, Dr.
Bharti Gawali "Classification of Fluent and
Dysfluent Speech Using KNN Classifier"
International Journal of Advanced Research in
Computer Science and Software Engineering
Volume 4, Issue 9, September 2014
[2.] Monica Mundada, Bharti Gawali,
Sangramsing Kayte "Recognition and
classification of speech and its related fluency
disorders" International Journal of Computer
Science and Information Technologies
(IJCSIT)
[3.] Monica Mundada, Sangramsing Kayte
“Classification of speech and its related
fluency disorders Using KNN” ISSN2231-
0096 Volume-4 Number-3 Sept 2014
[4.] Sangramsing Kayte, Monica Mundada, Dr.
Charansing Kayte "Di-phone-Based
Concatenative Speech Synthesis System for
Hindi" International Journal of Advanced
Research in Computer Science and Software
Engineering -Volume 5, Issue 10, October-
2015
[5.] Sangramsing Kayte, Monica Mundada, Dr.
Charansing Kayte “Di-phone-Based
Concatenative Speech Synthesis Systems for
Marathi Language” OSR Journal of VLSI and
Signal Processing (IOSR-JVSP) Volume 5,
Issue 5, Ver. I (Sep –Oct. 2015), PP 76-81e-
ISSN: 2319 –4200, p-ISSN No. : 2319 –4197
www.iosrjournals.org
[6.] Hyunsong Chung andMark A. Huckvale,
“Linguistic factors affecting timing in Korean
with application to speech synthesis”, in
Eurospeech, Denmark, 2001.
[7.] Campbell, W., “Syllable-based Segmental
Durations”, In: G. Bailly, C. Beno it, and T.
Sawallis (Eds.), Talking machines: Theories,
models and designs, pp. 43-60, 1992.
[8.] Sangramsing Kayte, Monica Mundada, Dr.
Charansing Kayte "Implementation of Marathi
Language Speech Databases for Large
Dictionary" IOSR Journal of VLSI and Signal
Processing (IOSR-JVSP) Volume 5, Issue 6,
Ver. I (Nov -Dec. 2015), PP 40-45e-ISSN:
2319 –4200, p-ISSN No. : 2319 –4197
[9.] Sangramsing Kayte, Monica Mundada "Study
of Marathi Phones for Synthesis of Marathi
Speech from Text" International Journal of
Emerging Research in Management
&Technology ISSN: 2278-9359 (Volume-4,
Issue-10) October 2015.
[10.] Sangramsing Kayte, Monica Mundada, Dr.
Charansing Kayte "A Marathi Hidden-Markov
Model Based Speech Synthesis System" IOSR
Journal of VLSI and Signal Processing (IOSR-
JVSP) Volume 5, Issue 6, Ver. I (Nov -Dec.
2015), PP 34-39e-ISSN: 2319 –4200, p-ISSN
No. : 2319 –4197
[11.] Sangramsing Kayte, Monica Mundada, Dr.
Charansing Kayte " Performance Calculation
of Speech Synthesis Methods for Hindi
language IOSR Journal of VLSI and Signal
Processing (IOSR-JVSP) Volume 5, Issue 6,
7. Sangramsing Kayte Int. Journal of Engineering Research and Applications www.ijera.com
ISSN: 2248-9622, Vol. 5, Issue 11, (Part - 4) November 2015, pp.115-119
www.ijera.com 121 | P a g e
Ver. I (Nov -Dec. 2015), PP 13-19e-ISSN:
2319 –4200, p-ISSN No. : 2319 –4197
[12.] Sangramsing N.kayte “Marathi Isolated-
Word Automatic Speech Recognition System
based on Vector Quantization (VQ) approach”
101th Indian Science Congress Jammu
University 03th Feb to 07 Feb 2014.
[13.] Sangramsing Kayte, Dr. Bharti Gawali
“Marathi Speech Synthesis: A review”
International Journal on Recent and Innovation
Trends in Computing and Communication
ISSN: 2321-8169 Volume: 3 Issue: 6 3708 –
3711
[14.] Sangramsing Kayte, Monica Mundada,
Santosh Gaikwad, Bharti Gawali
"PERFORMANCE EVALUATION OF
SPEECH SYNTHESIS TECHNIQUES FOR
ENGLISH LANGUAGE " International
Congress on Information and Communication
Technology 9-10 October, 2015
[15.] Sangramsing Kayte, Monica Mundada, Dr.
Charansing Kayte "A Review of Unit
Selection Speech Synthesis International
Journal of Advanced Research in Computer
Science and Software Engineering -Volume 5,
Issue 10, October-2015
[16.] Taylor, P., R. Caley, and A.W. Black,“The
Edinburgh Speech Tools Library”,1.2.1
edition, University of
Edinburgh,http://www.cstr.ed.ac.uk/projects/sp
eechtools.html,2002.