Computational Models of Speech Pattern Processing

✍ Scribed by Roger K. Moore (auth.), Keith Ponting (eds.)

• Publisher: Springer-Verlag Berlin Heidelberg
• Year: 1999
• Tongue: English
• Leaves: 477
• Series: NATO ASI Series 169
• Edition: 1
• Category: Library

✦ Synopsis

This high-level collection of invited tutorial papers and contributed papers is based on a NATO workshop held in 1997. It surveys and discusses the latest techniques in the field of speech science and technology with a view to working toward a unifying theory of speech pattern processing. The tutorials presenting significant leading-edge research are a valuable resource for researchers and others wishing to extend their knowledge of the field. Most of the papers are sorted into two groups, approaching respectively from the acoustic and the linguistic perspectives. The acoustic papers include reviews of work on human perception, the state of the art in very-large-vocabulary recognition, connectionist and hybrid models, robust approaches, and speaker characteristics. The linguistic papers include work on psycholinguistics, language modeling and adaptation, the use of natural language knowledge sources, multilingual systems, and systems using speech technology.

✦ Table of Contents

Front Matter....Pages i-XXX
Speech Pattern Processing....Pages 1-9
Psycho-acoustics and Speech Perception....Pages 10-17
Acoustic Modelling for Large Vocabulary Continuous Speech Recognition....Pages 18-39
Tree-based Dependence Models for Speech Recognition....Pages 40-53
Connectionist and Hybrid Models for Automatic Speech Recognition....Pages 54-66
Computational Models for Auditory Speech Processing....Pages 67-77
Speaker Adaptation of CDHMMs Using Bayesian Learning....Pages 78-83
Discriminative Improvement of the Representation Space for Continuous Speech Recognition....Pages 84-89
Dealing with Loss of Synchronism in Multi-Band Continuous Speech Recognition Systems....Pages 90-95
K-Nearest Neighbours Estimator in a HMM-Based Recognition System....Pages 96-101
Robust Speech Recognition....Pages 102-111
Channel Adaptation....Pages 112-121
Speaker Characterization, Speaker Adaptation and Voice Conversion....Pages 122-131
Speaker Recognition....Pages 132-142
Application of Acoustic Discriminative Training in an Ergodic HMM for Speaker Identification....Pages 143-148
Comparison of Several Compensation Techniques for Robust Speaker Verification....Pages 149-156
Segmental Acoustic Modeling for Speech Recognition....Pages 157-172
Trajectory Representations and Acoustic Descriptions for a Segment-Modelling Approach to Automatic Speech Recognition....Pages 173-180
Suprasegmental Modelling....Pages 181-198
Computational Models for Speech Production....Pages 199-213
Articulatory Features and Associated Production Models Statistical Speech Recognition....Pages 214-224
Talker Normalization with Articulatory Analysis-by-Synthesis....Pages 225-232
The Psycholinguistics of Spoken Word Recognition....Pages 233-251
Issues in Using Models for Self Evaluation and Correction of Speech....Pages 252-258
The Use of the Maximum Likelihood Criterion in Language Modelling....Pages 259-279
Language Model Adaptation....Pages 280-303
Using Natural-Language Knowledge Sources in Speech Recognition....Pages 304-327
How May I Help You?....Pages 328-349
Introduction of Rules into a Stochastic Approach for Language Modelling....Pages 350-355
History Integration into Semantic Classification....Pages 356-361
Multilingual Speech Recognition....Pages 362-374
Toward ALISP: A proposal for Automatic Language Independent Speech Processing....Pages 375-388
Interactive Translation of Conversational Speech....Pages 389-403
Multimodal Speech Systems....Pages 404-430
Multimodal Interfaces for Multimedia Information Agents....Pages 431-439
Back Matter....Pages 440-449

✦ Subjects

Artificial Intelligence (incl. Robotics);Pattern Recognition;Simulation and Modeling;Language Translation and Linguistics;Statistics and Computing/Statistics Programs;Complexity