Speech Synthesis and Recognition is an easy to read introduction to the subjects of generating and interpreting speech for those who have no experience and wish to specialise in the area, and also for professionals in related fields.
Author(s): Wendy Holmes
Edition: 2nd ed
Publisher: Taylor & Francis
Year: 2001
Language: English
Pages: 317
City: London; New York
Book Cover......Page 1
Title......Page 4
Contents......Page 5
Preface to the First Edition......Page 14
Preface to the Second Edition......Page 16
List of Abbreviations......Page 18
Human Speech Communication......Page 20
Mechanisms and Models of Human Speech Production......Page 30
Mechanisms and Models of the Human Auditory System......Page 52
Digital Coding of Speech......Page 66
Message Synthesis from Stored Human Speech Components......Page 86
Phonetic synthesis by rule......Page 100
Speech Synthesis from Textual or Conceptual Input......Page 112
Introduction to automatic speech recognition: template matching......Page 128
Introduction to stochastic modelling......Page 146
Introduction to front-end analysis for automatic speech recognition......Page 178
Practical techniques for improving speech recognition performance......Page 188
Automatic speech recognition for large vocabularies......Page 202
Neural networks for speech recognition......Page 232
Recognition of speaker characteristics......Page 238
Applications and performance of current technology......Page 250
Future research directions in speech synthesis and recognition......Page 264
Further Reading......Page 274
References......Page 284
Solutions to Exercises......Page 296
Glossary......Page 302
Index......Page 306
