The Watson speech recognition engine

Author

Sharp, R. Douglas ; Bocchieri, Enrico ; Castillo, Cecilia ; Parthasarathy, S. ; Rath, Chris ; Riley, Michael ; Rowland, James

Author_Institution

AT&T Bell Labs., Murray Hill, NJ, USA

Volume

5

fYear

1997

fDate

21-24 Apr 1997

Firstpage

4065

Abstract

In 1995, AT&T Research (then within Bell Labs) began work on a software-only automated speech recognition system named Watson(TM). The goal was ambitious; Watson was to serve as a single code base supporting applications ranging from PC-desktop command and control through to scaleable telephony interactive voice services. Furthermore, the software was to be the new code base for the research group, allowing fast deployment of new algorithmic advances from the lab into the field. A set of C++ objects has been developed which support these objectives. This paper gives an overview of the Watson automatic speech recognizer software architecture, describes the algorithms employed, and provides performance numbers for some sample tasks

Keywords

command and control systems; interactive systems; microcomputer applications; software engineering; speech recognition; telecommunication computing; telephony; AT&T Research; Bell Labs; C++ objects; PC desktop command and control; Watson speech recognition engine; algorithms; automatic speech recognizer; performance; scaleable telephony interactive voice services; software architecture; software only automated speech recognition system; Application software; Automatic speech recognition; Engines; Maximum likelihood decoding; Software algorithms; Software architecture; Speech recognition; Speech synthesis; Telephony; Viterbi algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.604839

Filename

604839