Enhancing speech in reverberation by steady-state suppression

Technical Report of IEICE Japan, Vol. EA2007-3, pp. 11-16, 2007 (in Japanese)

Enhancing speech in reverberation by steady-state suppression

K. Takahashi, K. Yasu, N. Hodoshima, T. Arai and K. Kurisu

Abstract: In order to improve speech intelligibility in reverberation, steady-state suppression was proposed by Arai et al. [Proc. Autumn Meet. Acoust. Soc. Jpn., 2001; Acoust. Sci. Tech., 2002]. On the other hand, a consonant enhancement technique for real-time processing in noise was proposed by Yasutake et al. [Tech. Rep. of IEICE Japan, 2005]. Our ultimate goal is to implement steady-state suppression in real-time. We discussed whether these two techniques are treated within a single unified framework because suppressing energy in vowels essentially enhancing consonants. As a result, we confirmed that the consonant detection method used in Yasutake et al. was included in steady-state suppression for real-time processing.

Keywords: speech enhancement, vowel suppression, reverberation, real-time processing

[PDF (887 kB)]