Comparison of standard and hybrid modeling techniques for distributed speech recognition

Author

Stadermann, Jan ; Rigoll, Gerhard

Author_Institution

Dept. of Comput. Sci., Duisburg Univ., Germany

fYear

2001

fDate

2001

Firstpage

143

Lastpage

146

Abstract

Distributed speech recognition (DSR) is an interesting technology for mobile recognition tasks where the recognizer is split up into two parts and connected by a transmission channel. We compare the performance of standard and hybrid modeling approaches in this environment. The evaluation is done on clean and noisy speech samples taken from the TI digits and the Aurora databases. Our results show that, for this task, the hybrid modeling techniques can outperform standard continuous systems.

Keywords

acoustic noise; acoustic signal processing; channel coding; distributed processing; feature extraction; hidden Markov models; mobile radio; speech recognition; vector quantisation; HMM; Mel-frequency cepstrum coefficients; channel coding; distributed speech recognition; feature extraction; hidden Markov models; hybrid modeling techniques; mobile phones; noisy speech samples; portable computers; vector quantization; Bandwidth; Bit rate; Channel coding; Computer science; Databases; Hidden Markov models; Mobile computing; Speech recognition; Vector quantization; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Speech Recognition and Understanding, 2001. ASRU '01. IEEE Workshop on

Print_ISBN

0-7803-7343-X

Type

conf

DOI

10.1109/ASRU.2001.1034608

Filename

1034608