Multilingual Text-to-Speech Synthesis: The Bell Labs Approach [Hardcover]

Richard Sproat (Editor)

Book Description

ISBN-10: 0792380274 | ISBN-13: 978-0792380276 | Publication Date: October 31, 1997 | Edition: 1

Multilingual Text-to-Speech Synthesis: The Bell Labs Approach is the first monograph-length description of the Bell Labs work on multilingual text-to-speech synthesis. Every important aspect of the system is described, including text analysis, segmental timing, intonation and synthesis. There is also a discussion of evaluation methodologies, as well as a chapter outlining some future areas of research. While the book focuses on the Bell Labs approach to the various problems of converting from text into speech, other approaches are discussed and compared. Thus, this book serves both the function of providing a single reference to an important strand of research in multilingual synthesis, while at the same time providing a source of information on current trends in the field. Chapters in this work were contributed by Richard Sproat, Jan van Santen, Bernd Möbius, Chilin Shih, Joseph Olive, Evelyne Tzoukermann, all of Bell Labs, and Kazuaki Maeda of the University of Pennsylvania.

Product Details

• Hardcover: 328 pages
• Publisher: Springer; 1 edition (October 31, 1997)
• Language: English
• ISBN-10: 0792380274
• ISBN-13: 978-0792380276
• Product Dimensions: 9.3 x 6.2 x 1 inches
• Shipping Weight: 1.3 pounds (View shipping rates and policies)
• Average Customer Review: 5.0 out of 5 stars  See all reviews (2 customer reviews)
• Amazon Best Sellers Rank: #3,374,329 in Books (See Top 100 in Books)

Customer Reviews

Most Helpful Customer Reviews

1 of 1 people found the following review helpful:

5.0 out of 5 stars An excellent work about the influential Bell Labs TTS, August 11, 1998

By A Customer

This review is from: Multilingual Text-to-Speech Synthesis: The Bell Labs Approach (Hardcover)

This work is an excellent overview of the Bell Labs approach to Text-to-Speech synthesis covering many languages. Certain to be a long-term influential work, as it clearly discusses each aspect of the multilingual system and the weighted finite state transduction (WFST) methods that make up the coherent approach. Topics include text analysis, prosodic modeling, WFSTs, system architecture, and acoustic realization issues.

1 of 2 people found the following review helpful:

5.0 out of 5 stars excellent survey, May 5, 1999

By A Customer

This review is from: Multilingual Text-to-Speech Synthesis: The Bell Labs Approach (Hardcover)

This is an excellent survey of the AT&T/Bell Labs TTS methods, particularily the WFST techniques. I am surprised, however, that little discussion is devoted to *stochastic* methods. For example, the sentence, "The deer was rotting on Ridgedale Dr.", might have the "Dr." expanded to "Doctor" and not "Drive" by the application of a trigram language model trained on a text corpus rather than the "ad hoc" application of hand-crafted rules (whether implemented as WFST's or not).