TY - GEN
T1 - Non-stationary noise estimation method based on bias-residual component decomposition for robust speech recognition
AU - Fujimoto, Masakiyo
AU - Watanabe, Shinji
AU - Nakatani, Tomohiro
PY - 2011
Y1 - 2011
N2 - This paper addresses a noise suppression problem, namely the estimation of non-stationary noise sequences. In this problem, we assume that non-stationary noise can be decomposed into stationary and non-stationary components. These components are described respectively as the bias factor and the residual signal between the bias component and noise at each frame. This decomposition clarifies the role of each component, thus enabling us to apply a suitable parameter estimation technique to each component. In this paper, the bias component is estimated by the EM algorithm with the entire observed signal sequence. On the other hand, the residual component is sequentially estimated by multiplying the extended Kalman filter with the EM algorithm. In the evaluation results, we confirmed that the proposed method improved speech recognition accuracy compared with the noise estimation methods without component decomposition.
AB - This paper addresses a noise suppression problem, namely the estimation of non-stationary noise sequences. In this problem, we assume that non-stationary noise can be decomposed into stationary and non-stationary components. These components are described respectively as the bias factor and the residual signal between the bias component and noise at each frame. This decomposition clarifies the role of each component, thus enabling us to apply a suitable parameter estimation technique to each component. In this paper, the bias component is estimated by the EM algorithm with the entire observed signal sequence. On the other hand, the residual component is sequentially estimated by multiplying the extended Kalman filter with the EM algorithm. In the evaluation results, we confirmed that the proposed method improved speech recognition accuracy compared with the noise estimation methods without component decomposition.
KW - component decomposition
KW - noise suppression
KW - nonstationary noise
KW - speech recognition
UR - http://www.scopus.com/inward/record.url?scp=80051616431&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80051616431&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2011.5947433
DO - 10.1109/ICASSP.2011.5947433
M3 - Conference contribution
AN - SCOPUS:80051616431
SN - 9781457705397
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 4816
EP - 4819
BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Y2 - 22 May 2011 through 27 May 2011
ER -