Recent Research Towards Advanced Man-Machine Interface Through Spoken Language (eBook)

Front Cover 1
Recent Research Towards Advanced Man-Machine Interface Through Spoken Language 4
Copyright Page 5
CONTENTS 14
Preface 6
List of Contributors 8
Chapter 1. Overview 18
Overview of Japanese Efforts Toward an Advanced Man-Machine Interface Through Spoken Language 20
Chapter 2. Speech Analysis 32
Composite Cosine Wave Analysis and its Application to Speech Signal 34
Smoothed Group Delay Analysis and its Applications to Isolated Word Recognition 44
A New Method of Speech Analysis — PSE 58
Estimation of Voice Source and Vocal Tract Parameters Based on ARMA Analysis and a Model for the Glottal Source Waveform . 69
Estimation of Sound Pressure Distribution Characteristics in the Vocal Tract 78
Speech Production Model Involving the Subglottal Structure and Oral-Nasal Coupling due to Wall Vibration 89
On the Analysis of Predictive Data such as Speech by a Class of Single Layer Connectionist Models 100
Chapter 3. Feature Extraction 118
Phoneme Recognition in Continuous Speech Using Feature Selection Based on Mutual Information 120
Dependency of Vowel Spectra on Phoneme Environment 132
A Preliminary Study on a New Acoustic Feature Model for Speech Recognition 141
A Hybrid Code for Automatic Speech Recognition 151
Complementary Approaches to Acoustic-Phonetic Decoding of Continuous Speech 162
Is Rule-Based Acoustic-Phonetic Speech Recognition a Dead End ? 177
Chapter 4. Speech Recognition 182
Speaker-Independent Phoneme Recognition Using Network Units Based on the a Posteriori Probability 184
Unsupervised Speaker Adaptation in Speech Recognition 194
A Japanese Text Dictation System Based on Phoneme Recognition and a Dependency Grammar 210
Word Recognition Using Synthesized Templates 222
A Cache-Based Natural Language Model for Speech Recognition 236
On the Design of a Voice-Activated Typewriter in French 246
Speech Recognition Using Hidden Markov Models: a CMU Perspective 266
Phonetic Features and Lexical Access 284
Chapter 5. Speech Understanding 300
A Large-Vocabulary Continuous Speech Recognition System with High Prediction Capability 302
Syntax/Semantics-Orientated Spoken Japanese Understanding System: SPOJUS-SYNO/SEMO 314
An Application of Discourse Analysis to Speech Understanding 328
Chapter 6. Speech Synthesis 336
Studies on Glottal Source and Formant Trajectory Models for the Synthesis of High Quality Speech 338
A System for Synthesis of High-Quality Speech from Japanese Text 357
A Text-to-Speech System Having Several Prosody Options: GK-SS5 373
A Prolog-Based Automatic Text-to-Phoneme Conversion System for British English 383
Data-Bank Analysis of Speech Prosody 394
Chapter 7. Dialogue Systems 402
Parsing Grammatically Ill-Formed Utterances 404
A Dialogue Analyzing Method Using a Dialogue Model 418
Discourse Management System for Communication Through Spoken Language 432
Towards Habitable Systems: Use of World Knowledge to Dynamically Constrain Speech Recognition 441
Chapter 8. Speech Enhancement 456
Noise Elimination of Speech by Vector Quantization and Neural Networks 458
Speech/Nonspeech Discrimination Under Nonstationary Noise Environments 469
Spatially Selective Multi-Microphone System 478
Chapter 9. Evaluation 486
Classification of Japanese Syllables Including Speech Sounds Found in Loanwords 488
A Study of the Suitability of Synthetic Speech for Proof-Reading in Relation to the Voice Quality 496
Improving Synthetic Speech Quality by Systematic Evaluation 506
Chapter 10. Speech Database 518
Considerations on a Common Speech Database 520
Transcription and Alignment of the TIMIT Database . 532