An introduction to recent results of Japanese research and development in the fields of speech synthesis.

4.2.2. Voice Conversion Based on Piecewise Linear Conversion Rules of Formant Frequency [Mizuno-95] -- Making Formant Frequency Conversion Rules (off-line procedures) -- Voice Conversion Algorithm (on-line procedures) -- 4.2.3. Performance Evaluation -- References -- Index

Automatic Speech Translation introduces recent results of Japanese research and development in speech translation and speech recognition. Topics covered include: fundamental concepts of speech recognition; speech pattern representation; phoneme-based HMM phoneme recognition; continuous speech recognition; speaker adaptation; speaker-independent speech recognition; utterance analysis, utterance transfer, utterance generation; contextual processing; speech synthesis and an experimental system of speech translation. This book presents the complicated technological aspects of machine translation and speech recognition, and outlines the future directions of this rapidly developing area of technology.

For a machine to convert text into sounds that humans can understand as speech requires an enormous range of components, from abstract analysis of discourse structure to synthesis and modulation of the acoustic output. Work in the field is thus inherently interdisciplinary, involving linguistics, computer science, acoustics, and psychology. This collection of articles by leading researchers in each of the fields involved in text-to-speech synthesis provides a picture of recent work in laboratories throughout the world and of the problems and challenges that remain. By providing samples of synthesized speech as well as video demonstrations for several of the synthesizers discussed, the book will also allow the reader to judge what all the work adds up to -- that is, how good is the synthetic speech we can now produce? Topics covered include: Signal processing and source modeling Linguistic analysis Articulatory synthesis and visual speech Concatenative synthesis and automated segmentation Prosodic analysis of natural speech Synthesis of prosody Evaluation and perception Systems and applications.

The major task of this book is a sociophonetic exploration of voice pitch characteristics of speakers across the cultures of Japan and America. This volume makes a cogent argument for the socio-cultural role of voice pitch in the expression of emotion and politeness and how culture and gender can intersect with each other. The book tenders acoustic phonetic evidence (as well as discourse analyses) in construing how an individual's voice pitch modulation utilized in conversational speech is reflected in this intersection as it demonstrates several methodological innovations crucial for sociophonetic research. Observations of people's voice pitch commonly made impressionistically not only contribute to this prosodic feature's perceptual stereotypes, but also inform us about our attitudes towards certain voice pitch characteristics. This volume includes an extensive review of these impressionistic remarks and acoustic phonetic investigations of voice pitch initiated in the early 20th century in the two nations, the latter of which contributed to both confirming and reconsidering the former. The volume further alludes to how attitudinal differences between these cultures were found to surface in the acoustically measured voice pitch modulation patterns obtained for this volume, stressing that voice pitch is capable of revealing various socio-cultural aspects of human behaviors.