CMU wearable computers for real-time speech translation

Author

Smailagic, Asim ; Siewiorek, Dan ; Reilly, Denis

Author_Institution

Carnegie Mellon Univ., Pittsburgh, PA, USA

Volume

8

Issue

2

fYear

2001

fDate

4/1/2001 12:00:00 AM

Firstpage

6

Lastpage

12

Abstract

Carnegie Mellon´s Wearable Computers Laboratory has built four generations of real-time speech translation wearable computers, culminating in the Speech Translator Smart Module. Smart Modules use a family of interoperable modules supporting real-time speech recognition, language translation, and speech synthesis. We examine the effect of various design factors on performance with emphasis on modularity and scalability. A system-level approach to power/performance optimization is described that improved the metric of (performance/(weight*volume*power)) by over a factor of 300 through the four generations

Keywords

language translation; optimisation; portable computers; speech recognition; speech synthesis; CMU wearable computers; Carnegie Mellon Wearable Computers Laboratory; Speech Translator Smart Module; interoperable modules; language translation; power/performance optimization; real-time speech recognition; real-time speech translation; scalability; speech synthesis; system-level approach; Application software; Cardiology; Delay; Instruction sets; Natural languages; Speech processing; Speech recognition; Speech synthesis; Strontium; Wearable computers;

fLanguage

English

Journal_Title

Personal Communications, IEEE

Publisher

ieee

ISSN

1070-9916

Type

jour

DOI

10.1109/98.918088

Filename

918088