An improved (Auto:I, LSP:T) constrained iterative speech enhancement for colored noise environments

Author

Pellom, Bryan L. ; Hansen, John H L

Author_Institution

Dept. of Electr. Eng., Duke Univ., Durham, NC, USA

Volume

6

Issue

6

fYear

1998

fDate

11/1/1998 12:00:00 AM

Firstpage

573

Lastpage

579

Abstract

We illustrate how the (Auto:I, LSP:T) constrained iterative speech enhancement algorithm can be extended to provide improved performance in colored noise environments. The modified algorithm, referred to as noise adaptive (Auto:I, LSP:T), operates on subband signal components in which the terminating iteration is adjusted based on the a posteriori estimate of the signal-to-noise ratio (SNR) in each signal subband. The enhanced speech is formulated as a combined estimate from individual signal subband estimators. The algorithm is shown to improve objective speech quality in additive noise environments over the traditional constrained iterative (Auto:I, LSP:T) enhancement formulation

Keywords

acoustic noise; iterative methods; maximum likelihood estimation; speech enhancement; (Auto:I, LSP:T) constrained iterative speech enhancement; a posteriori estimate; additive noise environments; colored noise environments; constrained iterative Auto-LSP speech enhancement algorithm; enhanced speech; noise adaptive (Auto:I, LSP:T); objective speech quality; performance; signal subband estimators; signal-to-noise ratio; subband signal components; subbanded signal components; terminating iteration; Acoustic noise; Background noise; Colored noise; Degradation; Iterative algorithms; Iterative methods; Signal to noise ratio; Speech enhancement; Speech processing; Working environment noise;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.725324

Filename

725324