| |
| |
| Preface | |
| |
| |
| |
| About Speech | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| How Speech Is Produced | |
| |
| |
| |
| The Vocal Tract | |
| |
| |
| |
| Articulatory Phonetics | |
| |
| |
| |
| Phonetic Alphabets | |
| |
| |
| |
| Prosody and Suprasegmentals | |
| |
| |
| |
| Syllables | |
| |
| |
| |
| Dialects | |
| |
| |
| |
| Languages (Other Than English) | |
| |
| |
| |
| Acoustic Phonetics | |
| |
| |
| |
| Phonemics | |
| |
| |
| |
| Articulatory Processes | |
| |
| |
| References | |
| |
| |
| |
| Representing Speech in the Computer | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Microphones | |
| |
| |
| |
| Sampling | |
| |
| |
| |
| Sampling Rate | |
| |
| |
| |
| Quantization | |
| |
| |
| |
| Speech Digitization | |
| |
| |
| |
| Wave Form Coders | |
| |
| |
| |
| Voice Coders (Vocoders) | |
| |
| |
| |
| The Frequency Domain | |
| |
| |
| |
| The Game of Jumble: Spectrum-Cepstrum, Frequency-Quefrency, Filtering-Liftering | |
| |
| |
| |
| Spectrograms: A Hybrid Representation of Speech | |
| |
| |
| References | |
| |
| |
| |
| Speech Recognition | |
| |
| |
| |
| Introduction | |
| |
| |
| |
| Speech Recognition: What It Is; What It Isn't | |
| |
| |
| |
| Why Is Speech Recognition Easy for Us and Difficult for Our Computers? | |
| |
| |
| |
| A Brief History of Speech Recognition | |
| |
| |
| |
| The Era of ARPA | |
| |
| |
| |
| After ARPA | |
| |
| |
| |
| Three Dimensions of Speech Recognition | |
| |
| |
| |
| Continuous Versus Noncontinuous | |
| |
| |
| |
| Speaker-Independent Versus Speaker-Dependent | |
| |
| |
| |
| Vocabulary Size | |
| |
| |
| |
| Tradeoffs and Interactions | |
| |
| |
| |
| Units of Speech Recognition | |
| |
| |
| |
| Words and Phrases | |
| |
| |
| |
| Syllables | |
| |
| |
| |
| Phonemes | |
| |
| |
| |
| Diphones and Triphones | |
| |
| |
| |
| Representing the Units | |
| |
| |
| |
| Acoustic Features | |
| |
| |
| |
| Comparing the Units | |
| |
| |
| |
| Dynamic Time Warping (DTW) | |
| |
| |
| |
| Hidden Markov Models (HMMs) | |
| |
| |
| |
| Future Challenges I | |
| |
| |
| |
| Artificial Neural Networks (ANNs) | |
| |
| |
| |
| Errors | |
| |
| |
| |
| Types of Errors | |
| |
| |
| |
| Error Tolerances | |
| |
| |
| |
| Performance Evaluation of Speech Recognizers | |
| |
| |
| |
| Error Rates | |
| |
| |
| |
| Other Factors | |
| |
| |
| |
| Error Reduction | |
| |
| |
| |
| Environmental Effects | |
| |
| |
| |
| Human Factors | |
| |
| |
| |
| Subsetting | |
| |
| |
| |
| Vocabulary Selection | |
| |
| |
| |
| Error Detection and Correction | |
| |
| |
| |
| Feedback Systems | |
| |
| |
| |
| Higher Levels of Linguistic Knowledge | |
| |
| |
| |
| Automatic Error Correction | |
| |
| |
| |
| Future Challenges II | |
| |
| |
| References | |
| |
| |
| |
| Speech Synthesis | |
| |
| |
| |
| Introduction and History | |
| |
| |
| |
| Parametric Coding (Electronic Synthesis) | |
| |
| |
| |
| Parameters of Parametric Speech Synthesis | |
| |
| |
| |
| Input Units of Parametric Speech Synthesis | |
| |
| |
| |
| Concatenative Synthesis | |
| |
| |
| |
| Allophone Concatenation | |
| |
| |
| |
| Diphone Concatenation | |
| |
| |
| |
| Demisyllable Concatenation | |
| |
| |
| |
| Waveform of Concatenative Units | |
| |
| |
| |
| Text-to-Speech Processing | |
| |
| |
| |
| Rules and Exceptions | |
| |
| |
| |
| Morphological Analysis | |
| |
| |
| |
| Articulation Effects | |
| |
| |
| |
| Prosody | |
| |
| |
| |
| Special Problems | |
| |
| |
| |
| Concept-to-Speech | |
| |
| |
| |
| Languages of the World | |
| |
| |
| |
| Dialects | |
| |
| |
| |
| Performance Evaluation | |
| |
| |
| |
| Intelligibility | |
| |
| |
| |
| Comprehensibility | |
| |
| |
| |
| Pleasantness/Naturalness | |
| |
| |
| |
| Future Challenges | |
| |
| |
| References | |
| |
| |
| |
| Speaker Recognition, Language Identification, and Lip Synchronization | |
| |
| |
| |
| Speaker Recognition | |
| |
| |
| |
| Speaker Recognition Versus Speech Recognition | |
| |
| |
| |
| Types of Speaker Recognition | |
| |
| |
| |
| Text-Dependent, Text-Independent, and Text-Prompted Speaker Recognition | |
| |
| |
| |
| "Voiceprints" | |
| |
| |
| |
| Methods of Speaker Recognition | |
| |
| |
| |
| Noise | |
| |
| |
| |
| Performance Evaluation of Speaker Recognition Systems | |
| |
| |
| |
| Co-channel Speaker Separation | |
| |
| |
| |
| Language Identification | |
| |
| |
| |
| Four Computational Approaches to Language Identification | |
| |
| |
| |
| Performance Evaluation of Language Identification Systems | |
| |
| |
| |
| Lip Synchronization | |
| |
| |
| |
| Visemes | |
| |
| |
| |
| Mapping Directly From the Speech Signal to Mouth Shapes | |
| |
| |
| |
| Future Challenges | |
| |
| |
| References | |
| |
| |
| |
| Applications in Speech Recognition | |
| |
| |
| |
| Criteria for a Viable Speech Recognition Application | |
| |
| |
| |
| Hands Busy, Eyes Busy | |
| |
| |
| |
| Remoteness | |
| |
| |
| |
| Miniaturization | |
| |
| |
| |
| 2001 Won't Be 2001 | |
| |
| |
| |
| The Role of Human Factors in Speech Recognition Applications | |
| |
| |
| |
| Application Areas | |
| |
| |
| |
| Assistive Technology | |
| |
| |
| |
| Telecommunications | |
| |
| |
| |
| Command and Control | |
| |
| |
| |
| Data Entry and Retrieval | |
| |
| |
| |
| Education | |
| |
| |
| References | |
| |
| |
| |
| Applications in Speech Synthesis | |
| |
| |
| |
| "At the Tone, the Time Will Be..." | |
| |
| |
| |
| When To Use Text-to-Speech; When To Use Digitally Recorded Speech | |
| |
| |
| |
| Interactive Voice Response Systems (IVRs) | |
| |
| |
| |
| Human Factors Revisited | |
| |
| |
| |
| Application Areas | |
| |
| |
| |
| Aid for Persons With Disabilities | |
| |
| |
| |
| Education | |
| |
| |
| |
| Emergency Scenarios | |
| |
| |
| |
| En Masse Advisories | |
| |
| |
| |
| Information Retrieval | |
| |
| |
| |
| Information Reporting | |
| |
| |
| |
| Electronic Mail and Fax Readers | |
| |
| |
| |
| In the Dark | |
| |
| |
| |
| Toys and Games | |
| |
| |
| |
| Transportation | |
| |
| |
| |
| Government Services | |
| |
| |
| |
| Disguise | |
| |
| |
| References | |
| |
| |
| |
| Applications in Speaker Recognition, Language Identification, and Lip Synchronization | |
| |
| |
| |
| Applications in Speaker Recognition | |
| |
| |
| |
| Access | |
| |
| |
| |
| Authentication | |
| |
| |
| |
| Monitoring | |
| |
| |
| |
| Fraud Prevention | |
| |
| |
| |
| Forensics | |
| |
| |
| |
| Personal Services | |
| |
| |
| |
| Applications in Language Identification | |
| |
| |
| |
| Telecommunications | |
| |
| |
| |
| Communications Monitoring | |
| |
| |
| |
| Public Information Systems | |
| |
| |
| |
| Applications in Automatic Lip Synching | |
| |
| |
| |
| Animation | |
| |
| |
| References | |
| |
| |
| Glossary | |
| |
| |
| About the Author | |
| |
| |
| Index | |