Speech-to-Speech Translation: A Massively Parallel Memory-Based Approach

✍ Scribed by Hiroaki Kitano (auth.)

• Publisher: Springer US
• Year: 1994
• Tongue: English
• Leaves: 204
• Series: The Springer International Series in Engineering and Computer Science 260
• Edition: 1
• Category: Library

✦ Synopsis

Speech--to--Speech Translation: a Massively Parallel Memory-BasedApproach describes one of the world's first successful speech--to--speech machine translation systems. This system accepts speaker-independent continuous speech, and produces translations as audio output. Subsequent versions of this machine translation system have been implemented on several massively parallel computers, and these systems have attained translation performance in the milliseconds range.
The success of this project triggered several massively parallel projects, as well as other massively parallel artificial intelligence projects throughout the world.
Dr. Hiroaki Kitano received the distinguished `Computers and Thought Award' from the International Joint Conferences on Artificial Intelligence in 1993 for his work in this area, and that work is reported in this book.

✦ Table of Contents

Front Matter....Pages i-xix
Introduction....Pages 1-12
Current Research Toward Speech-to-Speech Translation....Pages 13-27
Design Philosophy Behind the ΦDMDIALOG System....Pages 29-46
The ΦDMDIALOG System....Pages 47-113
DMSNAP: An Implementation on the Snap Semantic Network Array Processor....Pages 115-133
ASTRAL: An Implementation on the IXM2 Associative Memory Processor....Pages 135-155
Memoir: An Alternative View....Pages 157-171
Conclusion....Pages 173-176
Back Matter....Pages 177-193

✦ Subjects

Language Translation and Linguistics; Artificial Intelligence (incl. Robotics); Computational Linguistics