An energy-constrained signal subspace method for speech enhancement and recognition in colored noise

Author

Huang, Jun ; Zhao, Yunxin

Author_Institution

Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana, IL, USA

Volume

1

fYear

1998

fDate

12-15 May 1998

Firstpage

377

Abstract

An energy-constrained signal subspace (ECSS) method is proposed for speech enhancement and recognition under an additive colored noise condition. The key idea is to match the short-time energy of the enhanced speech signal to the unbiased estimate of the short-time energy of the clean speech, which is proven very effective for improving the estimation of the noise-like, low-energy segments in the speech signal. The colored noise is modelled by an autoregressive (AR) process. A modified covariance method is used to estimate the AR parameters of the colored noise and a prewhitening filter is constructed based on the estimated parameters. The performance of the proposed algorithm was evaluated using the TI46 digit database and the TIMIT continuous speech database. It was found that the ECSS method can significantly improve the signal-to-noise ratio (SNR) and word recognition accuracy (WRA) for isolated digits and continuous speech under various SNR conditions

Keywords

autoregressive processes; correlation methods; covariance analysis; filtering theory; noise; speech enhancement; speech recognition; AR parameters; AR process; SNR; TI46 digit database; TIMIT continuous speech database; additive colored noise; algorithm; autoregressive process; clean speech; correlation matrix; energy-constrained signal subspace method; enhanced speech signal; isolated digits; modified covariance method; noise-like low-energy segments; performance; prewhitening filter; short-time energy; signal-to-noise ratio; speech enhancement; speech recognition; unbiased estimate; word recognition accuracy; Acoustic noise; Additive noise; Colored noise; Filters; Parameter estimation; Signal processing; Signal to noise ratio; Speech analysis; Speech enhancement; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Seattle, WA

ISSN

1520-6149

Print_ISBN

0-7803-4428-6

Type

conf

DOI

10.1109/ICASSP.1998.674446

Filename

674446