Random House Publishing Group
Search
Expand Mobile Menu
Statistical Methods for Speech Recognition

Statistical Methods for Speech Recognition

About the Book



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.

Bradford Books imprint
Read more
Close

Language, Speech, and Communication Series

Statistical Methods for Speech Recognition
Children with Specific Language Impairment, second edition
The Syntax of American Sign Language
Toward a Cognitive Semantics, Volume 1
The Syntactic Process
Presumptive Meanings
Type-Logical Semantics
The Generative Lexicon

About the Author

Frederick Jelinek
More by Frederick Jelinek
Decorative Carat

By clicking submit, I acknowledge that I have read and agree to Penguin Random House's Privacy Policy and Terms of Use and understand that Penguin Random House collects certain categories of personal information for the purposes listed in that policy, discloses, sells, or shares certain personal information and retains personal information in accordance with the policy. You can opt-out of the sale or sharing of personal information anytime.

Random House Publishing Group