Talker Variability in Speech Processing
Unique in its approach, Talker Variability in Speech Processing embraces the differences in speech patterns without treating them as unwanted variables. The editors take on the difficult task of converting the mapping of speech patterns into mental representations. They cover theories of perception and cognition, issues in clinical speech pathology, and the practical concerns of speech technology. A radical departure from traditional approaches to speech processing, this text will strike a major chord for those surrounded by the dissonance of speech perception and language processing issues.
- Hardback | 256 pages
- 159.5 x 235.2 x 21.6mm | 651.92g
- 15 Jan 1997
- Elsevier Science Publishing Co Inc
- Academic Press Inc
- San Diego, United States
Table of contents
Complex representations ised in speech processing - overview of the book; some thoughts on "normalization" in speech perception; words and voices - perception and production in episodic lexicon; on the nature of perceptual adjustment to voice; listening to voices - theory and practice in voice perception research; talker normalization - phonetic constancy as a cognitive process; normalization of vowels by breath sounds; speech perception without speaker normalization - an exemplar model; speaker modeling for speaker adaptation in automatic speech recognition; overcoming speaker variability in automatic speech recognition - the speaker adaptation approach; vocal tract normalization for articulatory recovery and adaptation.
The editors have assembled an outstanding sample of research on the linguistic, perceptual, technological and clinical impact of differences among talkers. Their timely, superb collection presents a diversity of viewpoints and methods on a topic of increasing importance. This is a very useful book. --ROBERT REMEZ, Barnard College, Columbia University, New York, New York This book provides a valuable overview of important problems of speaker variability that affect virtually all aspects of speech research. --TERRANCE M. NEARY, University of Alberta, Edmonton, Canada
About Keith Johnson
Keith Johnson (Ph.D., The Ohio State University) has taught at the University of Alabama at Birmingham, UCLA, Indiana University, and the University of Illinois. He has published papers in the Journal of the Acoustic Society of America, the Journal of Phonetics, and Phonetica, among others. He teaches in the Linguistics Department at The Ohio State University. John Mullennix (Ph.D., SUNY Buffalo) has published research on speech processing and word recognition in, among other journals, Contemporary Psychology, Memory and Cognition, and the Journal of the Acoustic Society of America. He teaches in the Psychology Department at Wayne State University, and his home page is http://www science/wayne/edu/jmulleni.