이중채널 잡음음성인식을 위한 공간정보를 이용한 통계모델 기반 음성구간 검출
Statistical Model-Based Voice Activity Detection Using Spatial Cues for Dual-Channel Noisy Speech Recognition
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, voice activity detection (VAD) for dual-channel noisy speech recognition is proposed in which spatial cues are employed. In the proposed method, a probability model for speech presence/absence is constructed using spatial cues obtained from dual-channel input signal, and a speech activity interval is detected through this probability model. In particular, spatial cues are composed of interaural time differences and interaural level differences of dual-channel speech signals, and the probability model for speech presence/absence is based on a Gaussian kernel density. In order to evaluate the performance of the proposed VAD method, speech recognition is performed for speech segments that only include speech intervals detected by the proposed VAD method. The performance of the proposed method is compared with those of several methods such as an SNR-based method, a direction of arrival (DOA) based method, and a phase vector based method. It is shown from the speech recognition experiments that the proposed method outperforms conventional methods by providing relative word error rates reductions of 11.68%, 41.92%, and 10.15% compared with SNR-based, DOA-based, and phase vector based method,respectively.
Abstract
In this paper, voice activity detection (VAD) for dual-channel noisy speech recognition is proposed in which spatial cues are employed. In the proposed method, a probability model for speech presence/absence is constructed using spatial cues obtained from dual-channel input signal, and a speech activity interval is detected through this probability model. In particular, spatial cues are composed of interaural time differences and interaural level differences of dual-channel speech signals, and the probability model for speech presence/absence is based on a Gaussian kernel density. In order to evaluate the performance of the proposed VAD method, speech recognition is performed for speech segments that only include speech intervals detected by the proposed VAD method. The performance of the proposed method is compared with those of several methods such as an SNR-based method, a direction of arrival (DOA) based method, and a phase vector based method. It is shown from the speech recognition experiments that the proposed method outperforms conventional methods by providing relative word error rates reductions of 11.68%, 41.92%, and 10.15% compared with SNR-based, DOA-based, and phase vector based method,respectively.
참고문헌 (17)
- Le Bouquin-Jeannès, R., "Study of voice activity detector and its influence on a noise reduction system", Speech Communication, 16(3), pp.245~254 (1995)
- "ETSI TS 101 707 V7.5.0 (2000). Digital Cellular Telecommunications System (Phase 2+); Discontinuous Transmission (DTX) for Adaptive Multi-Rate (AMR) Speech Traffic Channels", ~ (2000)
- Junqua, J.-C., "A robust algorithm for word boundary detection in the presence of noise", IEEE Transactions on Speech and Audio Processing, 2(3), pp.406~412 (1994)
- Rabiner, L. R., "An algorithm for determining the endpoints of isolated utterances", Bell System Technical Journal, 54(2), pp.297~315 (1975)
- Mak, B., "A robust speech", non-speech detection algorithm using time and frequency-based features, 1992, pp.통권 : 1, 269~272
- "ETSI Standard (2007). Speech Processing, Transmission and Quality Aspects (STQ); Distributed Speech Recognition; Advanced Front-end Feature Extraction Algorithm; Compression Algorithms. ETSI ES 202 050 V1.1.5", ~ (2007)
- Ramírez, J., "Efficient voice activity detection algorithms using long-term speech information", Speech Communication, 42(3), pp.271~287 (2004)
- de la Torre, A., "Noise robust model-based voice activity detection", Proc. of Interspeech, pp.1954~1957 (2006)
- Tuker, R., "Voice activity detection using a periodicity measure", IEE Proceedings-I, Communications, Speech, and Vision, 139(4), pp.377~380 (1992)
- Davis, A., "Statistical voice activity detection using low-variance spectrum estimation and an adaptive threshold", IEEE Transactions on Audio, Speech, and Language Processing, 14(2), pp.412~424 (2006)
- Rubio, J. E., "Two-microphone voice activity detection based on the homogeneity of the direction of arrival estimates", Proc. ICASSP, 통권 : 4, pp.385~388 (2007)
- Kim, G., "Voice activity detection using phase vector in microphone array", Electronic Letters, 43(14), pp.783~784 (2007)
- An Efficient Auditory Filterbank Based on the Gammatone Functions, "Patterson, R. D.", MRC, Applied Psychology Unit, ~, pp.APU Report 2341 (2007)
- Glasberg B. R., "Derivation of auditory filter shapes from notched-noise data", Hearing Research, 47(1), pp.103~138 (1990)
- Parzen, E., "On estimation of a probability density function and mode", The Annals of Mathematical Statistics, 33(3), pp.1065~1076 (1962)
- 김상훈, "공통음성 DB구축", 한국음향학회 하계학술대회논문집, 21(1), pp.21~24 (2002)
- Gardner, W. G., "HRTF measurements of a KEMAR", Journal of the Acoustical Society of America, 97(6), pp.3907~3908 (1995)