Multichannel parametric speech enhancement

S. Srinivasan, R. Aichner, W.B. Kleijn, W. Kellermann

Research output: Contribution to journalArticleAcademicpeer-review

12 Citations (Scopus)
108 Downloads (Pure)

Abstract

We present a parametric model-based multichannel approach for speech enhancement. By employing an autoregressive model for the speech signal and using a trained codebook of speech linear predictive coefficients, minimum mean square error estimation of the speech signal is performed. By explicitly accounting for steering errors in the signal model, robust estimates are obtained. Experiments show that the proposed method results in significant performance gains.
Original languageEnglish
Pages (from-to)304-307
Number of pages4
JournalIEEE Signal Processing Letters
Volume13
Issue number5
DOIs
Publication statusPublished - 2006

Fingerprint Dive into the research topics of 'Multichannel parametric speech enhancement'. Together they form a unique fingerprint.

Cite this