Publication View

Reviewed by (2007)

Abstract
This is a weighty book in more senses than one. At nearly 600 pages (plus an ac-companying CD-ROM), it has the space to range very widely over the field of speech synthesis. The chapters comprise a selection of the papers presented at the Second ESCA/IEEE/AAAI Workshop on Text-to-Speech Synthesis in 1994 at Mohonk, New Jerse ~ U.S.A. (which was organized by the editors of this book). The work represented covers many laboratories in several countries. This makes for a snapshot of the state of speech synthesis research across the globe rather than at only one site. There are eight sections, each preceded by one or two "section introduction " chap-ters. Including the latter, there are a total of 46 chapters. The eight sections are as follows: 1. Signal processing and source modelling 2. Linguistic analysis 3. Articulatory synthesis and visual speech 4. Concatenative synthesis and automated segmentation 5. Prosodic analysis of natural speech

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.13.9115
Source http://acl.ldc.upenn.edu/J/J98/J98-3007.pdf
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Keywords languages or varieties, such as German, Japanese, French, Swedish, Italian, Mandarin
Type text
Language English
Relation 10.1.1.77.9314, 10.1.1.33.4840, 10.1.1.14.7146, 10.1.1.14.4707