Noise PSD Estimation Using Blind Source Separation in a Diffuse Noise Field

Konferenz: IWAENC 2012 - International Workshop on Acoustic Signal Enhancement
04.09.2012-06.09.2012 in Aachen, Germany

Tagungsband: IWAENC 2012

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Wang, Lin; Gerkmann, Timo; Doclo, Simon (University of Oldenburg, Institute of Physics, Signal Processing Group, Oldenburg, Germany)

This paper considers the problem of two-channel speech enhancement with a single target speaker in a diffuse noise field and proposes a novel algorithmfor estimating the power spectral density (PSD) of the background noise. First, a reference noise signal is computed as the output of a blocking matrix based on blind source separation (BSS). Then the ratio between the target noise PSD and the reference noise PSD is calculated by exploiting the separation matrix obtained from BSS and the spatial coherence of the noise field which is assumed to be known. The proposed algorithm can also operate during speech active periods, which is advantageous especially in fast-changing non-stationary noise fields. Experimental results show that the proposed algorithm outperforms existing methods, both in terms of noise PSD estimation and noise suppression. Index Terms — Noise estimation, diffuse noise field, blind source separation, speech enhancement