MuLiST : Multi-Lingual Speech Translator Batch Members: Apinaya Prethi K N (070105122005) Dhilip C (070105122015) Pavithra R (070105122066) Jan 2, 2011 Department Of Computer Science and Engineering Project Guide: Mr. Prabhakar M.E  Lecturer CSE Batch no : 22 Review no : Zero
Objective To design a speech-to-speech translator, which can translate speech from any language into English Speech.  MuLiST (Multi-Lingual Speech Translator)  can also be configured by the end-user to recognize and translate new languages.  Jan 2, 2011 Department Of Computer Science and Engineering
Abstract MuLiST, a Spoken Language Translator (SLT) is a module that recognises the speech of source language, compares it with the templates, converts it into templates of the destination language, synthesizes the target language and speaks it. Jan 2, 2011 Department Of Computer Science and Engineering
Introduction Translation is the communication of the meaning of a source-language by means of an equivalent target-language. A Spoken Language Translator (SLT) is a module that encapsulates both Natural Language Processing (NLP) and a Translator. Jan 2, 2011 Department Of Computer Science and Engineering
Existing Features Language definition can only be configured by the programmers and is not configurable by  the user. Only the developers can add any new languages, which is usually a complicated process. Custom language definitions, templates and dictionaries cannot be shared with other users. Jan 2, 2011 Department Of Computer Science and Engineering
Proposed Features To build a user configurable language definition system, were an end-user can also add a new language. To incorporate learning element in the system to automatically adopt according to users. To build a new feature that enables users to share their custom language definition, templates and dictionaries with other users of the system. Jan 2, 2011 Department Of Computer Science and Engineering
Algorithm and Methodology Sound sound = new Sound() Template template = Template(sound) While(rw ! = null) { RecoWords rw = RecoWords(template) Words words = +Words(rw) } Synthesize(words) Jan 2, 2011 Department Of Computer Science and Engineering
Conclusion This paper provides the methodologies and tools for the translation of source language into target language and thereby allow users to share and customize their language libraries. It also allows end users to add and configure a new language. Jan 2, 2011 Department Of Computer Science and Engineering
References Bowen Zhou, Yuqing Gao, Liang Gu,“IBM MASTOR SYSTEM: Multilingual Automatic Speech-to-speech Translator.” Gao Y , J. Sorensen, H. B. Zhou Z. Diao, “A Trainable Approach for Multi-Lingual Speech-To-Speech Translation System” Ruiqiang Zhang. Genichiro Kikui and Hirofumi Yamamoto, “A Unified Approach in Speech-to-Speech Translation: Integrating Features of Speech Recognition and Machine Translation” Jan 2, 2011 Department Of Computer Science and Engineering
Contd. C# 4 and .NET 4, First Edition, Wrox professional. http://msdn.microsoft.com/en-us/library/ms723627%28v=vs.85%29.aspx http://msdn.microsoft.com/en-us/default Jan 2, 2011 Department Of Computer Science and Engineering

MuLiST

  • 1.
    MuLiST : Multi-LingualSpeech Translator Batch Members: Apinaya Prethi K N (070105122005) Dhilip C (070105122015) Pavithra R (070105122066) Jan 2, 2011 Department Of Computer Science and Engineering Project Guide: Mr. Prabhakar M.E Lecturer CSE Batch no : 22 Review no : Zero
  • 2.
    Objective To designa speech-to-speech translator, which can translate speech from any language into English Speech. MuLiST (Multi-Lingual Speech Translator) can also be configured by the end-user to recognize and translate new languages. Jan 2, 2011 Department Of Computer Science and Engineering
  • 3.
    Abstract MuLiST, aSpoken Language Translator (SLT) is a module that recognises the speech of source language, compares it with the templates, converts it into templates of the destination language, synthesizes the target language and speaks it. Jan 2, 2011 Department Of Computer Science and Engineering
  • 4.
    Introduction Translation isthe communication of the meaning of a source-language by means of an equivalent target-language. A Spoken Language Translator (SLT) is a module that encapsulates both Natural Language Processing (NLP) and a Translator. Jan 2, 2011 Department Of Computer Science and Engineering
  • 5.
    Existing Features Languagedefinition can only be configured by the programmers and is not configurable by the user. Only the developers can add any new languages, which is usually a complicated process. Custom language definitions, templates and dictionaries cannot be shared with other users. Jan 2, 2011 Department Of Computer Science and Engineering
  • 6.
    Proposed Features Tobuild a user configurable language definition system, were an end-user can also add a new language. To incorporate learning element in the system to automatically adopt according to users. To build a new feature that enables users to share their custom language definition, templates and dictionaries with other users of the system. Jan 2, 2011 Department Of Computer Science and Engineering
  • 7.
    Algorithm and MethodologySound sound = new Sound() Template template = Template(sound) While(rw ! = null) { RecoWords rw = RecoWords(template) Words words = +Words(rw) } Synthesize(words) Jan 2, 2011 Department Of Computer Science and Engineering
  • 8.
    Conclusion This paperprovides the methodologies and tools for the translation of source language into target language and thereby allow users to share and customize their language libraries. It also allows end users to add and configure a new language. Jan 2, 2011 Department Of Computer Science and Engineering
  • 9.
    References Bowen Zhou,Yuqing Gao, Liang Gu,“IBM MASTOR SYSTEM: Multilingual Automatic Speech-to-speech Translator.” Gao Y , J. Sorensen, H. B. Zhou Z. Diao, “A Trainable Approach for Multi-Lingual Speech-To-Speech Translation System” Ruiqiang Zhang. Genichiro Kikui and Hirofumi Yamamoto, “A Unified Approach in Speech-to-Speech Translation: Integrating Features of Speech Recognition and Machine Translation” Jan 2, 2011 Department Of Computer Science and Engineering
  • 10.
    Contd. C# 4and .NET 4, First Edition, Wrox professional. http://msdn.microsoft.com/en-us/library/ms723627%28v=vs.85%29.aspx http://msdn.microsoft.com/en-us/default Jan 2, 2011 Department Of Computer Science and Engineering