Regression features for recognition of speech in quiet and in noise

Author

Applebaum, Ted H. ; Hanson, Brian A.

Author_Institution

Speech Technol. Lab., Santa Barbara, CA, USA

fYear

1991

fDate

14-17 Apr 1991

Firstpage

985

Abstract

It is proposed that the number of speech analysis frames used in calculating regression features should be controlled separately from the time length over which the features are calculated. Regression features are used to represent the first two time derivatives of the speech cepstrum in a speaker-independent, isolated-word recognition task. The recognition system is trained on normal (noise-free, non-Lombard) speech, but tested on normal, noisy, Lombard, or noisy-Lombard speech. It is shown that for recognition based on the combination of the first two regression features with the static cepstral coefficients, increasing the time length to more than 200 ms, using all of the frames in this time interval, resulted in the highest recognition rates for noisy-Lombard test speech

Keywords

noise; speech analysis and processing; speech intelligibility; speech recognition; statistical analysis; isolated-word recognition; noise free speech; noisy speech; noisy-Lombard speech; normal speech; regression features; speaker independent speech recognition; speech analysis frames; speech cepstrum; static cepstral coefficients; Additive noise; Cepstral analysis; Cepstrum; Laboratories; Noise reduction; Speech analysis; Speech enhancement; Speech recognition; Testing; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on

Conference_Location

Toronto, Ont.

ISSN

1520-6149

Print_ISBN

0-7803-0003-3

Type

conf

DOI

10.1109/ICASSP.1991.150506

Filename

150506