Sixth European Conference on Speech Communication and Technology

Budapest, Hungary
September 5-9, 1999

Speech Enhancement Using Nonlinear Microphone Array under Nonstationary Noise Conditions

Hiroshi Saruwatari (1), Shoji Kajita (2), Kazuya Takeda (1), Fumitada Itakura (2)

(1) Graduate School of Engineering/CIAIR; (2) Center for Information Media Studies/CIAIR, Nagoya University Furo-cho, Chikusa-ku, Nagoya, Japan

This paper describes a spatial spectral subtraction method by using the complementary beamforming microphone array to enhance noisy speech signals for speech recognition. The complementary beamforming is based on two types of beamformers de-signed to obtain complementary directivity patterns with respect to each other. In this paper, it is shown that the nonlinear subtraction processing with complementary beamforming can result in a kind the spectral subtraction without the need for speech pause detection. To evaluate the effectiveness, speech enhancement exper-iments and speech recognition experiments are performed based on computer simulations under both stationary and nonstationary noise conditions. In comparison with the optimized conventional delay-and-sum array, it is shown that: (1) the proposed array performs more than 20% better in word recognition rates under the conditions that the white Gaussian noise is used, (2) the proposed array improves the word recognition rate by about 5% when the interfering noise is a single speaker or the overlap of some speakers, (3) the proposed array improves the word recognition rate by more than 10% when the noise is a nonstationary bubble noise.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Saruwatari, Hiroshi / Kajita, Shoji / Takeda, Kazuya / Itakura, Fumitada (1999): "Speech enhancement using nonlinear microphone array under nonstationary noise conditions", In EUROSPEECH'99, 2567-2570.