- Research Article
- Open Access
A Semi-Continuous State-Transition Probability HMM-Based Voice Activity Detector
EURASIP Journal on Audio, Speech, and Music Processing volume 2007, Article number: 043218 (2007)
We introduce an efficient hidden Markov model-based voice activity detection (VAD) algorithm with time-variant state-transition probabilities in the underlying Markov chain. The transition probabilities vary in an exponential charge/discharge scheme and are softly merged with state conditional likelihood into a final VAD decision. Working in the domain of ITU-T G.729 parameters, with no additional cost for feature extraction, the proposed algorithm significantly outperforms G.729 Annex B VAD while providing a balanced tradeoff between clipping and false detection errors. The performance compares very favorably with the adaptive multirate VAD, option 2 (AMR2).
Benyassine A, Shlomot E, Su H-Y, Massaloux D, Lamblin C, Petit J-P: ITU-T recommendation G.729 Annex B: a silence compression scheme for use with G.729 optimized for V.70 digital simultaneous voice and data applications. IEEE Communications Magazine 1997,35(9):64-73. 10.1109/35.620527
Cho YD, Kondoz A: Analysis and improvement of a statistical model-based voice activity detector. IEEE Signal Processing Letters 2001,8(10):276-278. 10.1109/97.957270
Sohn J, Kim NS, Sung W: A statistical model-based voice activity detection. IEEE Signal Processing Letters 1999,6(1):1-3. 10.1109/97.736233
Nemer E, Gourbran R, Mahmoud S: Robust voice activity detection using higher-order statistics in the LPC residual domain. IEEE Transactions on Speech and Audio Processing 2001,9(3):217-231. 10.1109/89.905996
Marzinzik M, Kollmeier B: Speech pause detection for noise spectrum estimation by tracking power envelope dynamics. IEEE Transactions on Speech and Audio Processing 2002,10(2):109-118. 10.1109/89.985548
Yang S, Li Z-G, Chen Y-Q: A fractal based voice activity detector for internet telephone. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '03), April 2003, Hong Kong 1: 808-811.
ITU-T G.729 Annex B : A silence compression scheme for G.729 optimized for terminals conforming to recommendation V.70. 1996.
Beritelli F, Casale S, Ruggeri G, Serrano S: Performance evaluation and comparison of G.729/AMR/fuzzy voice activity detectors. IEEE Signal Processing Letters 2002,9(3):85-88. 10.1109/97.995824
Beritelli F, Casale S, Cavallaro A: A robust voice activity detector for wireless communications using soft computing. IEEE Journal on Selected Areas in Communications 1998,16(9):1818-1829. 10.1109/49.737650
Gazor S, Zhang W: A soft voice activity detector based on a Laplacian-Gaussian model. IEEE Transactions on Speech and Audio Processing 2003,11(5):498-505. 10.1109/TSA.2003.815518
ETSI EN 301 708 v7.1.1 (1999-12) : European Standard (Telecommunications series), Digital cellular telecommunications system (Phase 2+); Voice Activity Detector (VAD) for Adaptive Multi-Rate (AMR) speech traffic channels; General description. (GSM 06.94 version 7.1.1 Release 1998)
Kelly GE, Lindsey JK: Models for estimating the change-point in gas exchange data. Proceedings of the 22nd Conference on Applied Statistics in Ireland (CASI '02), May 2002, Antrim, Ireland
ITU-T Series P Supplement 23, "ITU-T coded-speech database," February 1998, http://www.itu.int
Othman H, Aboulnasr T: A Gaussian/Laplacian hybrid statistical voice activity detector for line spectral frequency-based speech coders. Proceedings of the 46th IEEE International Midwest Symposium on Circuits and Systems (MWSCAS '03), December 2003, Cairo, Egypt 2: 693-696.
Othman H, Aboulnasr T: A semi-continuous state transition probability HMM-based voice activity detection. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '04), May 2004, Montreal, Quebec, Canada 5: 821-824.
Tian Y, Wu J, Wang Z, Lu D: Fuzzy clustering and Bayesian information criterion based threshold estimation for robust voice activity detection. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '03), April 2003, Hong Kong 1: 444-447.