This book is the result of the second NATO Advanced Study Institute on speech processing held at the Chateau de Bonas, France, from June 29th to July 10th, 1981. This Institute provided a high-level coverage of the fields of speech transmission, recognition and understanding, which constitute important areas where research activity has re­ cently been associated with actual industrial developments. This book will therefore include both fundamental and applied topics. Ten survey papers by some of the best specialists in the field are included. They give an up-to-date presentation of several important problems in automatic speech processing. As a consequence the book can be considered as a reference manual on some important areas of automatic speech processing. The surveys are indicated by 'a * in the table of contents. This book also contains research papers corresponding to original works, which were presented during the panel sessions of the Institute. For the sake of clarity the book has been divided into five sections : 1. Speech Analysis and Transmission: An emphasis has been laid on the techniques of linear prediction (LPC), and the problems involved in the transmission of speech at various bit rates are addressed in details. 2. Acoustics and Phonetics : One'of the major bottleneck in the development of speech recogni­ tion systems remains the transcription of the continuous speech wave into some discrete strings or lattices of phonetic symbols. Two survey papers discuss this problem from different points of view and several practical systems are also described.

Inhalt

§ 1. Speech Analysis and Transmission.- Linear Prediction of Speech and its Application to Speech Processing.- Medium and Low Bit Rate Speech Transmission.- Algorithms and Devices for Pitch Determination of Speech Signals.- § 2. Acoustics and Phonetics.- Acoustic-phonetic Decoding and Adaptation in Continuous Speech Recognition.- Acoustic-phonetic Knowledge Representation: Implications from Spectrogram Reading Experiments.- Phonetic Recognition by Linear Prediction: Experiences at ENST.- Acoustic-phonetic Analysis Based on an Articulatory Model.- The Efficiency of Demisyllable Segmentation in the Recognition of Spoken Words.- Interaction between Auditory, Syllabic and Lexical Knowledge in a Speech Understanding System.- § 3. Applications.- Speaker Independent Connected Word Recognition.- An Algorithm for Connected Word Recognition.- SERAPHINE: A connected Word Recognition System.- Implementation of Models for Speech Recognition with very Large Scale Integrated Circuit Technology.- § 4. Systems.- Self-organized continuous Speech Recognition.- The Erlangen Speech Understanding Project.- Semantic and Pragmatic Processing in Continuous Speech Understanding.- The ARIAL II Speech Recognition System.- § 5. Miscellaneous.- Speaker Recognition: A Survey.- Complexity of Algorithms and Pattern Recognition.- Selecting, Designing, and Using Practical Speech Recognizers.