Model-combination-based acoustic mapping

Author

Westphal, Martin ; Waibel, Alex

Author_Institution

Interactive Syst. Labs., Karlsruhe Univ., Germany

Volume

1

fYear

2001

fDate

2001

Firstpage

221

Abstract

We propose a method for compensating distortions in the speech signal caused by environment changes. The basic method concentrates on additive noise, but can be extended to address also channel and to some extent speaker changes. By combining compensation with adaptation techniques it leads to high error rate reductions for mobile speech applications. Thereby, it is more efficient than adapting the acoustic model of the recognizer and more powerful than simple noise reduction techniques

Keywords

Gaussian distribution; acoustic noise; compensation; covariance matrices; least mean squares methods; mobile radio; normal distribution; speech recognition; adaptation techniques; additive noise; channel changes; distortions; environment changes; high error rate reductions; mobile speech; model-combination-based acoustic mapping; speaker changes; speech signal; Acoustic distortion; Acoustic noise; Additive noise; Linear discriminant analysis; Loudspeakers; Noise robustness; Prototypes; Speech enhancement; Speech recognition; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01). 2001 IEEE International Conference on

Conference_Location

Salt Lake City, UT

ISSN

1520-6149

Print_ISBN

0-7803-7041-4

Type

conf

DOI

10.1109/ICASSP.2001.940807

Filename

940807