Codebook-based Bayesian speech enhancement for nonstationary environments

S. Srinivasan, J. Samuelsson, W.B. Kleijn

Research output: Contribution to journalArticleAcademicpeer-review

116 Citations (Scopus)
208 Downloads (Pure)

Abstract

In this paper, we propose a Bayesian minimum mean squared error approach for the joint estimation of the short-term predictor parameters of speech and noise, from the noisy observation. We use trained codebooks of speech and noise linear predictive coefficients to model the a priori information required by the Bayesian scheme. In contrast to current Bayesian estimation approaches that consider the excitation variances as part of the a priori information, in the proposed method they are computed online for each short-time segment, based on the observation at hand. Consequently, the method performs well in nonstationary noise conditions. The resulting estimates of the speech and noise spectra can be used in a Wiener filter or any state-of-the-art speech enhancement system. We develop both memoryless (using information from the current frame alone) and memory-based (using information from the current and previous frames) estimators. Estimation of functions of the short-term predictor parameters is also addressed, in particular one that leads to the minimum mean squared error estimate of the clean speech signal. Experiments indicate that the scheme proposed in this paper performs significantly better than competing methods
Original languageEnglish
Pages (from-to)441-452
Number of pages12
JournalIEEE Transactions on Audio, Speech, and Language Processing
Volume15
Issue number2
DOIs
Publication statusPublished - 2007

Fingerprint

Dive into the research topics of 'Codebook-based Bayesian speech enhancement for nonstationary environments'. Together they form a unique fingerprint.

Cite this