Keith M. Ponting Speech Research Unit, DERA Malvern St. Andrew's Road, Great Malvern, Worcs. WR14 3PS, UK email: ponting

Survey of state of the art in speech pattern processing Includes invited papers from leading scientists in the field Contains papers from both the acoustic and the linguistic perspectives Based on a NATO meeting working toward a unifying theory of speech pattern processing Includes supplementary material: sn.pub/extras

Inhalt
Speech Pattern Processing.- Psycho-acoustics and Speech Perception.- Acoustic Modelling for Large Vocabulary Continuous Speech Recognition.- Tree-based Dependence Models for Speech Recognition.- Connectionist and Hybrid Models for Automatic Speech Recognition.- Computational Models for Auditory Speech Processing.- Speaker Adaptation of CDHMMs Using Bayesian Learning.- Discriminative Improvement of the Representation Space for Continuous Speech Recognition.- Dealing with Loss of Synchronism in Multi-Band Continuous Speech Recognition Systems.- K-Nearest Neighbours Estimator in a HMM-Based Recognition System.- Robust Speech Recognition.- Channel Adaptation.- Speaker Characterization, Speaker Adaptation and Voice Conversion.- Speaker Recognition.- Application of Acoustic Discriminative Training in an Ergodic HMM for Speaker Identification.- Comparison of Several Compensation Techniques for Robust Speaker Verification.- Segmental Acoustic Modeling for Speech Recognition.- Trajectory Representations and Acoustic Descriptions for a Segment-Modelling Approach to Automatic Speech Recognition.- Suprasegmental Modelling.- Computational Models for Speech Production.- Articulatory Features and Associated Production Models in Statistical Speech Recognition.- Talker Normalization with Articulatory Analysis-by-Synthesis.- The Psycholinguistics of Spoken Word Recognition.- Issues in Using Models for Self Evaluation and Correction of Speech.- The Use of the Maximum Likelihood Criterion in Language Modelling.- Language Model Adaptation.- Using Natural-Language Knowledge Sources in Speech Recognition.- How May I Help You?.- of Rules into a Stochastic Approach for Language Modelling.- History Integration into Semantic Classification.- Multilingual Speech Recognition.- Toward ALISP: A proposal for Automatic Language Independent Speech Processing.- Interactive Translation of Conversational Speech.- Multimodal Speech Systems.- Multimodal Interfaces for Multimedia Information Agents.