TY - GEN
T1 - DNN BASED MULTIFRAME SINGLE-CHANNEL NOISE REDUCTION FILTERS
AU - Pan, Ningning
AU - Chen, Jingdong
AU - Benesty, Jacob
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - While multiframe noise reduction filters, e.g., the multiframe Wiener and minimum variance distortionless response (MVDR) ones, have demonstrated great potential to improve both the subband and fullband signal-to-noise ratios (SNRs) by exploiting explicitly the interframe speech correlation, the implementation of such filters requires the knowledge of the interframe correlation coefficients for every subband, which are challenging to estimate in practice. In this work, we present a deep neural network (DNN) based method to estimate the interframe correlation coefficients and the estimated coefficients are subsequently fed into multiframe filters to achieve noise reduction. Unlike existing DNN based methods, which outputs the enhanced speech directly, the presented method combines deep learning and traditional methods, which gives more flexibility to optimize or tune noise reduction performance. Experimental results are presented to justify the properties of the presented methods.
AB - While multiframe noise reduction filters, e.g., the multiframe Wiener and minimum variance distortionless response (MVDR) ones, have demonstrated great potential to improve both the subband and fullband signal-to-noise ratios (SNRs) by exploiting explicitly the interframe speech correlation, the implementation of such filters requires the knowledge of the interframe correlation coefficients for every subband, which are challenging to estimate in practice. In this work, we present a deep neural network (DNN) based method to estimate the interframe correlation coefficients and the estimated coefficients are subsequently fed into multiframe filters to achieve noise reduction. Unlike existing DNN based methods, which outputs the enhanced speech directly, the presented method combines deep learning and traditional methods, which gives more flexibility to optimize or tune noise reduction performance. Experimental results are presented to justify the properties of the presented methods.
KW - DNN
KW - Single-channel noise reduction
KW - interframe correlation
KW - multiframe MVDR filter
KW - multiframe Wiener filter
UR - http://www.scopus.com/inward/record.url?scp=85131234620&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9746063
DO - 10.1109/ICASSP43922.2022.9746063
M3 - 会议稿件
AN - SCOPUS:85131234620
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 8782
EP - 8786
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Y2 - 22 May 2022 through 27 May 2022
ER -