Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Design of Robust Subtractive Beamformer for Noisy Speech Recognition

Mitsunori Mizumachi (1), Masato Akagi (2), Satoshi Nakamura (1)

(1) ATR Spoken Language Translation Research Laboratories, Seika-cho, Souraku-gun, Kyoto, Japan (2) School of Information Science, Japan Advanced Institute of Science and Technology, Tatsunokuchi, Nomi-gun, Ishikawa, Japan

There is a big demand for noise reduction to enhance ASR robustness. A great variety of noise reduction methods have been proposed, but almost none of them can reduce non-stationary noises. The authers have proposed an algorithm that can reduce noises that former methods, such as adaptive beamformers, find diffcult to deal with. In this paper, the authors verify the proposed method as a front-end for ASR by phoneme recognition tests. Its feasibility is also discussed under reverberant environments.

Full Paper

Bibliographic reference.  Mizumachi, Mitsunori / Akagi, Masato / Nakamura, Satoshi (2000): "Design of robust subtractive beamformer for noisy speech recognition", In ICSLP-2000, vol.4, 57-60.