DOA 기반 학습률 조절을 이용한 다채널 음성개선 알고리즘
Multi-Channel Speech Enhancement Algorithm Using DOA-based Learning Rate Control
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV)algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark's scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.
Abstract
In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV)algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark's scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.
참고문헌 (11)
- Jeong, S, "Speech quality and recognition rate improvement in car noise environments", Electronics Letters, 37(12), pp.801~802 (2001)
- "ES 202 212 V1.1.2. Speech processing, transmission and quality aspects(STQ); distributed speech recognition; extended advanced front-end feature extraction algorithm; compression algorithm; back-end speech reconstruction algorithm", ETSI Standard, ~ (2005)
- Van Veen, B. D, "Beamforming: A versatile approach to spatial filtering", IEEE ASSP Magazine, 5(2), pp.4~24 (1998)
- Brandstein, M, "Microphone Arrays: Signal Processing Techniques and Applications" (2001), Springer
- Benesty, J, "Microphone Array Signal Processing (Springer Topics in Signal Processing)" (2008), Springer
- Hyvarinen, A, "Independent component analysis: Algorithms and applications", Neural Networks, 13(4), pp.411~430 (2000)
- 이영재, "확률적 목표 음성 검출을 통한 다채널 입력 기반 음성개선", 말소리와 음성과학, 1(3), pp.95~102 (2009), 한국음성학회
- 박지훈, "필터뱅크 기반 프로스트 알고리즘을 이용한 빔포밍 최적화", 말소리, 1(66), pp.73~86 (2008), 대한음성학회
- Hong, J, "Adaptive Microphone Array Processing for High-Performance Speech Recognition in Car Environment", IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 57(1), pp.260~266, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Wang, L, "Combining superdirective beamforming and frequency-domain blind source separation for highly reverberant signals", EURASIP Journal on Audio, Speech, and Music Processing, 2010, pp.1~13 (2010)
- Frost, O. L, "An algorithm for linearly constrained adaptive array processing", Proceedings of the IEEE, 60(8), pp.926~935 (1972)