Statistical Methods for Speech Recognition / Edition 1

Statistical Methods for Speech Recognition / Edition 1

by Frederick Jelinek, Jelinek
     
 

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-maximization algorithm, information theoretic goodness criteria, maximum entropy probability estimation, parameter and data clustering, and smoothing of

See more details below

Overview

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-maximization algorithm, information theoretic goodness criteria, maximum entropy probability 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.

The MIT Press

Product Details

ISBN-13:
9780262100663
Publisher:
MIT Press
Publication date:
01/16/1998
Series:
Language, Speech, and Communication
Edition description:
New Edition
Pages:
305
Product dimensions:
6.20(w) x 9.00(h) x 1.00(d)
Age Range:
18 Years

Table of Contents

Preface
Ch. 1The Speech Recognition Problem1
Ch. 2Hidden Markov Models15
Ch. 3The Acoustic Model39
Ch. 4Basic Language Modeling57
Ch. 5The Viterbi Search79
Ch. 6Hypothesis Search on a Three and the Fast Match93
Ch. 7Elements of Information Theory113
Ch. 8The Complexity of Tasks - The Quality of Language Models137
Ch. 9The Expectation-Maximization Algorithm and its Consequences147
Ch. 10Decision Trees and Tree Language Models165
Ch. 11Phonetics from Orthography: Spelling-to-Base Form Mappings197
Ch. 12Triphones and Allophones207
Ch. 13Maximum Entropy Probability Estimation and Language Models219
Ch. 14Three Applications of Maximum Entropy Estimation to Language Modeling245
Ch. 15Estimation of Probabilities from Counts and the Back-Off Method257
Name Index275
Subject Index279

Read More

Customer Reviews

Average Review:

Write a Review

and post it to your social network

     

Most Helpful Customer Reviews

See all customer reviews >