Jean-Paul Haton - Böcker

The domain of speech processing has come to the point where researchers and engineers are concerned with how speech technology can be applied to new products, and how this technology will transform our future. One important problem is to improve robustness of speech processing under adverse conditions, which is the subject of this book. Robust speech processing is a relatively new area which became a concern as technology started moving from laboratory to field applications. A method or an algorithm is robust if it can deal with a broad range of applications and adapt to unknown conditions. This text aims to address all of the fundamental problems and issues in the area. The book is divided into three parts. The first provides the background necessary for understanding the rest of the material. It also emphasizes the problems of speech production and perception in noise along with popular techniques used in speech analysis and automatic speech recognition. Part Two discusses the problems relevant to robustness in automatic speech recognition and speech-based applications.It emphasizes intra- and inter-speaker variability as well as automatic speech recognition of Lombard, noisy and channel distorted speech. Finally, the third part covers recent advances in the field of robust automatic speech recognition.

Foreword Looking back the past 30 years. we have seen steady progress made in the area of speech science and technology. I still remember the excitement in the late seventies when Texas Instruments came up with a toy named "Speak-and-Spell" which was based on a VLSI chip containing the state-of-the-art linear prediction synthesizer. This caused a speech technology fever among the electronics industry. Particularly. applications of automatic speech recognition were rigorously attempt­ ed by many companies. some of which were start-ups founded just for this purpose. Unfortunately. it did not take long before they realized that automatic speech rec­ ognition technology was not mature enough to satisfy the need of customers. The fever gradually faded away. In the meantime. constant efforts have been made by many researchers and engi­ neers to improve the automatic speech recognition technology. Hardware capabilities have advanced impressively since that time. In the past few years. we have been witnessing and experiencing the advent of the "Information Revolution." What might be called the second surge of interest to com­ mercialize speech technology as a natural interface for man-machine communication began in much better shape than the first one. With computers much more powerful and faster. many applications look realistic this time. However. there are still tremendous practical issues to be overcome in order for speech to be truly the most natural interface between humans and machines.

This book presents a selection of revised refereed papers taken from the contributions to the Second European Workshop on Case-Based Reasoning, EWCBR-94, held at the Abbaye de Royaumont near Paris in November 1994. The 22 papers included were chosen from a total of 60 submissions. The important evolution by experienced artificial intelligence during the last few years has been essentially influenced by case-based reasoning, particularly by the area of knowledge-based decision support. This book documents the progress achieved in CBR methods and tools during the very recent paSt. It also outlines the substantial success achieved in the applications domain, especially in the fields of architecture and computer-aided design, task planning, chemical synthesis, maintenance and diagnosis, and law.

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.