DocumentCode
900525
Title
Feature compensation based on soft decision
Author
Kim, Nam Soo ; Kim, Young Joon ; Kim, Hyun Woo
Author_Institution
Sch. of Electr. Eng., Seoul Nat. Univ., South Korea
Volume
11
Issue
3
fYear
2004
fDate
3/1/2004 12:00:00 AM
Firstpage
378
Lastpage
381
Abstract
In this letter, we propose a novel approach to feature compensation for robust speech recognition in noisy environments. Our approach combines the interacting multiple model (IMM) and spectral subtraction (SS) techniques based on a soft decision for speech presence. The proposed approach shows 13.56% of average relative improvement compared to the IMM algorithm in the speech recognition experiments performed on the AURORA2 database when clean condition training is applied.
Keywords
decision theory; spectral analysis; speech recognition; AURORA2 database; condition training; feature compensation; interacting multiple model; robust speech recognition; soft decision; spectral subtraction techniques; Background noise; Degradation; Noise level; Noise reduction; Noise robustness; Pattern recognition; Piecewise linear approximation; Speech enhancement; Speech recognition; Working environment noise;
fLanguage
English
Journal_Title
Signal Processing Letters, IEEE
Publisher
ieee
ISSN
1070-9908
Type
jour
DOI
10.1109/LSP.2003.821720
Filename
1268034
Link To Document