Robust noise estimation applied to different speech estimators

Author

Schwab, Markus ; Kim, Hyoung-Gook ; Wiryadi ; Noll, Peter

Author_Institution

Dept. of Commun. Syst., Tech. Univ. of Berlin, Germany

Volume

2

fYear

2003

fDate

9-12 Nov. 2003

Firstpage

1904

Abstract

In this paper we present robust noise estimation for speech enhancement algorithms. The robust noise estimation based on a modified minima controlled recursive averaging noise estimator was applied to different speech estimators. The investigated speech estimators were spectral subtraction (SS), log spectral amplitude speech estimator (LSA) and optimally modified log spectral amplitude estimator (OM-LSA). The performances of the different algorithms were measured both by the signal-to-noise ratio (SNR) and recognition accuracy of automatic speech recognition (ASR).

Keywords

amplitude estimation; noise; recursive estimation; spectral analysis; speech enhancement; speech recognition; SNR; automatic speech recognition; modified minima controlled recursive averaging noise estimator; optimally modified log spectral amplitude speech estimator; robust noise estimation; signal-to-noise ratio; spectral subtraction; speech enhancement algorithm; Amplitude estimation; Automatic speech recognition; Degradation; Noise reduction; Noise robustness; Recursive estimation; Signal to noise ratio; Speech enhancement; Speech recognition; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2004. Conference Record of the Thirty-Seventh Asilomar Conference on

Print_ISBN

0-7803-8104-1

Type

conf

DOI

10.1109/ACSSC.2003.1292313

Filename

1292313