A codec for speech recognition in a wireless system

Author

Reichl, W. Olfgang ; Eerackody, Vijitha W. ; Potamianos, Alexandros

Author_Institution

Lucent Technol. Bell Labs., Murray Hill, NJ, USA

fYear

2000

fDate

2000

Firstpage

34

Lastpage

37

Abstract

We consider a distributed speech recognition system where representative parameters of the speech signal are extracted at the wireless terminal and transmitted to a centralized automatic speech recognition (ASR) server. Several error protection schemes are proposed for the ASR feature stream. In addition, a “soft-feature” error concealment strategy is introduced at the ASR server that uses the marginal distribution of only the reliable features during likelihood computation. The performance of the error protection and concealment schemes is evaluated over typical cellular wireless channels and it is shown to reduce ASR error rate up to 65% for certain channels

Keywords

Gaussian channels; Rayleigh channels; cellular radio; error detection; forward error correction; quantisation (signal); radio networks; speech codecs; speech recognition; ASR feature stream; ASR server; Gaussian channels; automatic speech recognition server; cellular wireless channels; correlated Rayleigh channels; distributed speech recognition system; error protection schemes; error rate reduction; forward error correction; forward error detection; likelihood computation; marginal distribution; performance; soft-feature error concealment; speech codec; speech quantization; speech signal parameters; unequal error protection; wireless system; wireless terminal; Automatic speech recognition; Cepstral analysis; Degradation; Network servers; Protection; Quantization; Robustness; Speech analysis; Speech codecs; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

EUROCOMM 2000. Information Systems for Enhanced Public Safety and Security. IEEE/AFCEA

Conference_Location

Munich

Print_ISBN

0-7803-6323-X

Type

conf

DOI

10.1109/EURCOM.2000.874767

Filename

874767