Statistical Methods for Speech Recognition
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...
Search in google:
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.
PrefaceCh. 1The Speech Recognition Problem1Ch. 2Hidden Markov Models15Ch. 3The Acoustic Model39Ch. 4Basic Language Modeling57Ch. 5The Viterbi Search79Ch. 6Hypothesis Search on a Three and the Fast Match93Ch. 7Elements of Information Theory113Ch. 8The Complexity of Tasks - The Quality of Language Models137Ch. 9The Expectation-Maximization Algorithm and its Consequences147Ch. 10Decision Trees and Tree Language Models165Ch. 11Phonetics from Orthography: Spelling-to-Base Form Mappings197Ch. 12Triphones and Allophones207Ch. 13Maximum Entropy Probability Estimation and Language Models219Ch. 14Three Applications of Maximum Entropy Estimation to Language Modeling245Ch. 15Estimation of Probabilities from Counts and the Back-Off Method257Name Index275Subject Index279
