For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Speech Enhancement Using Nonlinear Microphone Array Based on Noise Adaptive Complementary Beamforming
Hiroshi SARUWATARI Shoji KAJITA Kazuya TAKEDA Fumitada ITAKURA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2000/05/25
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Engineering Acoustics
speech enhancement, microphone array, complementary beamforming, noise adaptation, spectral subtraction,
Full Text: PDF(1.2MB)>>
This paper describes an improved complementary beamforming microphone array based on the new noise adaptation algorithm. Complementary beamforming is based on two types of beamformers designed to obtain complementary directivity patterns with respect to each other. In this system, during a pause in the target speech, two directivity patterns of the beamformers are adapted to the noise directions of arrival so that the expectation values of each noise power spectrum are minimized in the array output. Using this technique, we can realize the directional nulls for each noise even when the number of sound sources exceeds that of microphones. To evaluate the effectiveness, speech enhancement experiments and speech recognition experiments are performed based on computer simulations with a two-element array and three sound sources under various noise conditions. In comparison with the conventional adaptive beamformer and the conventional spectral subtraction method cascaded with the adaptive beamformer, it is shown that (1) the proposed array improves the signal-to-noise ratio (SNR) of degraded speech by more than 6 dB when the interfering noise is two speakers with the input SNR of below 0 dB, (2) the proposed array improves the SNR by about 2 dB when the interfering noise is bubble noise, and (3) an improvement in the recognition rate of more than 18% is obtained when the interfering noise is two speakers or two overlapped signals of some speakers under the condition that the input SNR is 10 dB.