Taylor's Library

Normal view MARC view ISBD view

Statistical methods for speech recognition / Frederick Jelinek.

By: Jelinek, Frederick, 1932-.
Series: Language, speech, and communication. Publisher: Cambridge, Mass. : MIT Press, c1997Description: xxi, 283 p. ; 24 cm.ISBN: 0262100665.Subject(s): Automatic speech recognition -- Statistical methodsDDC classification: 006.454
Contents:
Preface. - Ch. 1. The Speech Recognition Problem. - Ch. 2. Hidden Markov Models. - Ch. 3. The Acoustic Model. - Ch. 4. Basic Language Modeling. - Ch. 5. The Viterbi Search. - Ch. 6. Hypothesis Search on a Three and the Fast Match. - Ch. 7. Elements of Information Theory. - Ch. 8. The Complexity of Tasks - The Quality of Language Models. - Ch. 9. The Expectation-Maximization Algorithm and its Consequences. - Ch. 10. Decision Trees and Tree Language Models. - Ch. 11. Phonetics from Orthography: Spelling-to-Base Form Mappings. - Ch. 12. Triphones and Allophones - Ch. 13. Maximum Entropy Probability Estimation and Language Models. - Ch. 14. Three Applications of Maximum Entropy Estimation to Language Modeling. - Ch. 15. Estimation of Probabilities from Counts and the Back-Off Method. - Name Index. - Subject Index.
Summary: This book reflects decades of important research on the mathematical foundations of speech recognition. It focuses on underlying statistical techniques such as hidden Markov models, decision trees, the expectation-maxmization algorithm, information theoretic goodness criteria, maximun entropy probalility estimation, parameter and data clustering, and smoothing of probability distributions. The author's goal is to present these principles clearly in the simplest setting, to show the advantages of self-organization from real data, and to enable the reader to apply the techniques. - Front cover
Item type Current location Call number Copy number Status Notes Date due Barcode Remark
Main Collection TU External Storage-LCS
006.454 JEL (Browse shelf) 1 Available LAWxx,17002,03,CL 5000064023 Please fill up online form at https://taylorslibrary.taylors.edu.my/services/external_storage1

Preface. - Ch. 1. The Speech Recognition Problem. - Ch. 2. Hidden Markov Models. - Ch. 3. The Acoustic Model. - Ch. 4. Basic Language Modeling. - Ch. 5. The Viterbi Search. - Ch. 6. Hypothesis Search on a Three and the Fast Match. - Ch. 7. Elements of Information Theory. - Ch. 8. The Complexity of Tasks - The Quality of Language Models. - Ch. 9. The Expectation-Maximization Algorithm and its Consequences. - Ch. 10. Decision Trees and Tree Language Models. - Ch. 11. Phonetics from Orthography: Spelling-to-Base Form Mappings. - Ch. 12. Triphones and Allophones - Ch. 13. Maximum Entropy Probability Estimation and Language Models. - Ch. 14. Three Applications of Maximum Entropy Estimation to Language Modeling. - Ch. 15. Estimation of Probabilities from Counts and the Back-Off Method. - Name Index. - Subject Index.

This book reflects decades of important research on the mathematical foundations of speech recognition. It focuses on underlying statistical techniques such as hidden Markov models, decision trees, the expectation-maxmization algorithm, information theoretic goodness criteria, maximun entropy probalility estimation, parameter and data clustering, and smoothing of probability distributions. The author's goal is to present these principles clearly in the simplest setting, to show the advantages of self-organization from real data, and to enable the reader to apply the techniques. - Front cover