TY - JOUR
T1 - AR-GARCH in presence of noise
T2 - Parameter estimation and its application to voice activity detection
AU - Mousazadeh, Saman
AU - Cohen, Israel
N1 - Funding Information: Manuscript received December 01, 2009; revised May 03, 2010; accepted August 17, 2010. Date of publication August 30, 2010; date of current version March 30, 2011. This work was supported by the Israel Science Foundation under Grant 1085/05. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Michael Lewis Seltzer.
PY - 2011
Y1 - 2011
N2 - This paper presents a new method for voice activity detection (VAD) based on the autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH) model. The speech signal is modeled as an AR-GARCH process in the time domain, and the likelihood ratio is computed and compared to a threshold. The time-varying variance of the speech signal needed for computing the likelihood function under speech presence hypothesis, is estimated using the AR-GARCH model. The model parameters are estimated using a novel technique based on the recursive maximum likelihood (RML) estimation. The variance of the additive noise, a critical issue in designing a VAD, is estimated using the improved minima controlled recursive averaging (IMCRA) method, which is properly modified to be applicable to noise variance estimation in the time domain. The performances of the VAD and the parameter estimation method are examined under several conditions. Experimental results indicate the robustness of the AR-GARCH based VAD both to noise variations and low signal-to-noise ratio (SNR) conditions.
AB - This paper presents a new method for voice activity detection (VAD) based on the autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH) model. The speech signal is modeled as an AR-GARCH process in the time domain, and the likelihood ratio is computed and compared to a threshold. The time-varying variance of the speech signal needed for computing the likelihood function under speech presence hypothesis, is estimated using the AR-GARCH model. The model parameters are estimated using a novel technique based on the recursive maximum likelihood (RML) estimation. The variance of the additive noise, a critical issue in designing a VAD, is estimated using the improved minima controlled recursive averaging (IMCRA) method, which is properly modified to be applicable to noise variance estimation in the time domain. The performances of the VAD and the parameter estimation method are examined under several conditions. Experimental results indicate the robustness of the AR-GARCH based VAD both to noise variations and low signal-to-noise ratio (SNR) conditions.
KW - Autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH)
KW - noisy data
KW - nonstationary noise
KW - parameter estimation
KW - voice activity detector (VAD)
UR - http://www.scopus.com/inward/record.url?scp=79953283970&partnerID=8YFLogxK
U2 - 10.1109/TASL.2010.2070494
DO - 10.1109/TASL.2010.2070494
M3 - مقالة
SN - 1558-7916
VL - 19
SP - 916
EP - 926
JO - IEEE Transactions on Audio, Speech and Language Processing
JF - IEEE Transactions on Audio, Speech and Language Processing
IS - 4
M1 - 5559370
ER -