12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Blind Speech Prior Estimation for Generalized Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator

Ryo Wakisaka (1), Hiroshi Saruwatari (1), Kiyohiro Shikano (1), Tomoya Takatani (2)

(1) NAIST, Japan
(2) Toyota Motor Corporation, Japan

In this paper, to achieve high-quality speech enhancement, we introduce the generalized minimum mean-square error short-time spectral amplitude estimator with a new blind prior estimation of the speech probability density function (p.d.f.). To deal with various types of speech signals with different p.d.f., we propose an algorithm of speech kurtosis estimation based on moment-cumulant transformation for blind adaptation to the shape parameter of speech p.d.f. From the objective and subjective evaluation experiments, we show the improved noise reduction performance of the proposed method.

Full Paper

Bibliographic reference.  Wakisaka, Ryo / Saruwatari, Hiroshi / Shikano, Kiyohiro / Takatani, Tomoya (2011): "Blind speech prior estimation for generalized minimum mean-square error short-time spectral amplitude estimator", In INTERSPEECH-2011, 361-364.