Speech recognition for an information kiosk

Author

Gauvain, J.-L. ; Gangolf, J.J. ; Lamel, L.

Author_Institution

Spoken Language Process. Group, CNRS, Orsay, France

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

849

Abstract

In the context of the ESPRIT MASK project one faces the problem of adapting a “state-of-the-art” laboratory speech recognizer for use in the real world with naive users. The speech recognizer is a software-only system that runs in real-time on a standard RISC processor. All aspects of the speech recognizer have been reconsidered from signal capture to adaptive acoustic models and language models. The resulting system includes such features as microphone selection, response cancellation, noise compensation, query rejection capability and decoding strategies for real-time recognition

Keywords

acoustic signal detection; decoding; public information systems; real-time systems; reduced instruction set computing; speech recognition; ESPRIT MASK project; adaptive acoustic models; adaptive language models; decoding strategies; information kiosk; laboratory speech recognizer adaptation; microphone selection; naive users; noise compensation; query rejection capability; real-time software-only system; response cancellation; signal capture; speech recognition; standard RISC processor; Face recognition; Laboratories; Microphones; Natural languages; Real time systems; Reduced instruction set computing; Software standards; Speech coding; Speech processing; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607734

Filename

607734