open access

https://hdl.handle.net/2115/39808

Improved Adaptive β-Order MMSE Speech Enhancement

Improved Adaptive Beta-Order MMSE Speech Enhancement

英語

2009-10-04

Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference, International Organizing Committee

Proceedings : APSIPA ASC 2009 : Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference

797-800

APSIPA ASC 2009: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference. 4-7 October 2009. Sapporo, Japan. Poster session: Speech Processing (7 October 2009).

This paper considers a single channel speech enhancement algorithm, which is based on our previous work on β-order minimum mean square error (MMSE) spectral estimation. We propose to make β a function of both local and frame signal-to-noise ratios (SNRs) in order to achieve more effective preservation of weak speech components. Moreover, by taking into account the speech-presence uncertainty in the adaptive β-order MMSE algorithm, we achieve a significant noise reduction and an improved spectral estimation of weak speech components. Experiments also show that the proposed estimator outperforms other well known speech enhancement algorithms.

会議発表論文

Version of Record