+612 9045 4394
 
CHECKOUT
Computer Speech Technology : Computing S. - Robert Rodman

Computer Speech Technology

Computing S.

Hardcover

Published: 1st January 1999
Ships: 7 to 10 business days
7 to 10 business days
RRP $187.99
$138.25
26%
OFF
or 4 easy payments of $34.56 with Learn more

Offers a non-technical overview of all the major areas in the computer processing of human speech: speech recognition; speech synthesis; speaker recognition; language identification, lip synchronisation; and co-channel separation. The text's intuitive approach uses illustrations, analogies, and both historical and state-of-the-art descriptions to explain relatively complex concepts. Specifically, it helps the reader learn the professional jargon used in different areas of speech processing, evaluate speech processing systems for specific applications, understand how the various technologies of speech processing actually work, identify practical applications for speech technology in the commercial world, and relate speech technology to actual spoken language.

Prefacep. xv
About Speechp. 1
Introductionp. 1
How Speech Is Producedp. 2
The Vocal Tractp. 2
Articulatory Phoneticsp. 5
Phonetic Alphabetsp. 14
Prosody and Suprasegmentalsp. 25
Syllablesp. 28
Dialectsp. 29
Languages (Other Than English)p. 31
Acoustic Phoneticsp. 34
Phonemicsp. 42
Articulatory Processesp. 47
Referencesp. 49
Representing Speech in the Computerp. 51
Introductionp. 51
Microphonesp. 52
Samplingp. 53
Sampling Ratep. 54
Quantizationp. 62
Speech Digitizationp. 69
Wave Form Codersp. 73
Voice Coders (Vocoders)p. 83
The Frequency Domainp. 87
The Game of Jumble: Spectrum-Cepstrum, Frequency-Quefrency, Filtering-Lifteringp. 91
Spectrograms: A Hybrid Representation of Speechp. 93
Referencesp. 98
Speech Recognitionp. 99
Introductionp. 99
Speech Recognition: What It Is; What It Isn'tp. 100
Why Is Speech Recognition Easy for Us and Difficult for Our Computers?p. 101
A Brief History of Speech Recognitionp. 103
The Era of ARPAp. 105
After ARPAp. 109
Three Dimensions of Speech Recognitionp. 111
Continuous Versus Noncontinuousp. 111
Speaker-Independent Versus Speaker-Dependentp. 113
Vocabulary Sizep. 114
Tradeoffs and Interactionsp. 115
Units of Speech Recognitionp. 117
Words and Phrasesp. 118
Syllablesp. 118
Phonemesp. 119
Diphones and Triphonesp. 120
Representing the Unitsp. 121
Acoustic Featuresp. 121
Comparing the Unitsp. 126
Dynamic Time Warping (DTW)p. 126
Hidden Markov Models (HMMs)p. 129
Future Challenges Ip. 133
Artificial Neural Networks (ANNs)p. 133
Errorsp. 137
Types of Errorsp. 138
Error Tolerancesp. 142
Performance Evaluation of Speech Recognizersp. 144
Error Ratesp. 145
Other Factorsp. 152
Error Reductionp. 154
Environmental Effectsp. 155
Human Factorsp. 155
Subsettingp. 158
Vocabulary Selectionp. 159
Error Detection and Correctionp. 160
Feedback Systemsp. 161
Higher Levels of Linguistic Knowledgep. 164
Automatic Error Correctionp. 170
Future Challenges IIp. 175
Referencesp. 176
Speech Synthesisp. 177
Introduction and Historyp. 177
Parametric Coding (Electronic Synthesis)p. 179
Parameters of Parametric Speech Synthesisp. 179
Input Units of Parametric Speech Synthesisp. 182
Concatenative Synthesisp. 184
Allophone Concatenationp. 186
Diphone Concatenationp. 186
Demisyllable Concatenationp. 187
Waveform of Concatenative Unitsp. 188
Text-to-Speech Processingp. 190
Rules and Exceptionsp. 191
Morphological Analysisp. 193
Articulation Effectsp. 194
Prosodyp. 196
Special Problemsp. 200
Concept-to-Speechp. 206
Languages of the Worldp. 208
Dialectsp. 209
Performance Evaluationp. 209
Intelligibilityp. 210
Comprehensibilityp. 211
Pleasantness/Naturalnessp. 212
Future Challengesp. 213
Referencesp. 213
Speaker Recognition, Language Identification, and Lip Synchronizationp. 215
Speaker Recognitionp. 215
Speaker Recognition Versus Speech Recognitionp. 216
Types of Speaker Recognitionp. 217
Text-Dependent, Text-Independent, and Text-Prompted Speaker Recognitionp. 218
"Voiceprints"p. 220
Methods of Speaker Recognitionp. 221
Noisep. 229
Performance Evaluation of Speaker Recognition Systemsp. 231
Co-channel Speaker Separationp. 234
Language Identificationp. 236
Four Computational Approaches to Language Identificationp. 238
Performance Evaluation of Language Identification Systemsp. 241
Lip Synchronizationp. 243
Visemesp. 244
Mapping Directly From the Speech Signal to Mouth Shapesp. 246
Future Challengesp. 249
Referencesp. 249
Applications in Speech Recognitionp. 251
Criteria for a Viable Speech Recognition Applicationp. 252
Hands Busy, Eyes Busyp. 252
Remotenessp. 253
Miniaturizationp. 255
2001 Won't Be 2001p. 255
The Role of Human Factors in Speech Recognition Applicationsp. 256
Application Areasp. 258
Assistive Technologyp. 259
Telecommunicationsp. 262
Command and Controlp. 264
Data Entry and Retrievalp. 268
Educationp. 272
Referencesp. 275
Applications in Speech Synthesisp. 277
"At the Tone, the Time Will Be..."p. 278
When To Use Text-to-Speech; When To Use Digitally Recorded Speechp. 278
Interactive Voice Response Systems (IVRs)p. 280
Human Factors Revisitedp. 281
Application Areasp. 282
Aid for Persons With Disabilitiesp. 283
Educationp. 286
Emergency Scenariosp. 287
En Masse Advisoriesp. 288
Information Retrievalp. 289
Information Reportingp. 290
Electronic Mail and Fax Readersp. 292
In the Darkp. 294
Toys and Gamesp. 295
Transportationp. 295
Government Servicesp. 296
Disguisep. 296
Referencesp. 296
Applications in Speaker Recognition, Language Identification, and Lip Synchronizationp. 297
Applications in Speaker Recognitionp. 298
Accessp. 298
Authenticationp. 301
Monitoringp. 301
Fraud Preventionp. 303
Forensicsp. 304
Personal Servicesp. 306
Applications in Language Identificationp. 307
Telecommunicationsp. 307
Communications Monitoringp. 307
Public Information Systemsp. 308
Applications in Automatic Lip Synchingp. 308
Animationp. 308
Referencesp. 310
Glossaryp. 311
About the Authorp. 331
Indexp. 333
Table of Contents provided by Syndetics. All Rights Reserved.

ISBN: 9780890062975
ISBN-10: 0890062978
Series: Computing S.
Audience: General
Format: Hardcover
Language: English
Number Of Pages: 362
Published: 1st January 1999
Publisher: Artech House Publishers
Country of Publication: US
Dimensions (cm): 23.4 x 15.6  x 2.0
Weight (kg): 0.68