Recognition experiments with the SpeechDat-Car Aurora Spanish database using 8 kHz- and 16 kHz-sampled signals

Author

Nadeu, Climent ; Tolos, Marta

Author_Institution

TALP Res. Center, Univ. Politecnica de Catalunya, Barcelona, Spain

fYear

2001

fDate

2001

Firstpage

135

Lastpage

138

Abstract

Like the other SpeechDat-Car databases, the Spanish one has been collected using a 16 kHz sampling frequency, and several microphone positions and environmental noises. We aim at clarifying whether there is any advantage in terms of recognition performance from processing the 16 kHz-sampled signals instead of the usual 8 kHz-sampled ones. Recognition tests have been carried out within the Aurora experimental framework, which includes signals from both a close-talking microphone and a distant microphone. Our preliminary results indicate that it is possible to get a performance improvement from the increased bandwidth in the noisy car environment.

Keywords

acoustic noise; channel bank filters; distributed processing; natural languages; signal sampling; speech recognition; 16 kHz; 8 kHz; Mel-frequency cepstral coefficients; SpeechDat-Car Aurora Spanish database; digit utterances; distributed speech recognition; filter-bank energies; frequency filtering; front-ends; noisy car environment; sampling frequency; spectral derivative parameters; Bandwidth; Databases; Frequency; Microphones; Sampling methods; Speech recognition; Standards development; Telecommunication standards; Testing; 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.2001.1034606

Filename

1034606