TY - GEN
T1 - Cabin Noise Separation Using an Improved Convolutional Time Domain Noise Separation Networks
AU - He, Qunyi
AU - Wang, Haitao
AU - Zeng, Xiangyang
AU - Chen, Kean
AU - Lei, Ye
AU - Ren, Shuwei
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Traditional acoustic signal separation techniques usually have high requirements for experimental conditions and economic costs. In this paper, an improved convolutional time domain noise separation networks is proposed for noise separation in the cabin environment based on the classical CONY-TasNet. Parallel dilated convolutions is designed in the separation layer to achieving relatively long time signal processing. Then, more envelope information can be obtained which is beneficial for enhancing the processing effect of cabin low-frequency noise and harmonic noise, and also reducing the loss of local noise information. Compared with other commonly used deep networks, the proposed networks has better separation results. It not only restores a more accurate spectrum structure, but also obtain smaller distortions.
AB - Traditional acoustic signal separation techniques usually have high requirements for experimental conditions and economic costs. In this paper, an improved convolutional time domain noise separation networks is proposed for noise separation in the cabin environment based on the classical CONY-TasNet. Parallel dilated convolutions is designed in the separation layer to achieving relatively long time signal processing. Then, more envelope information can be obtained which is beneficial for enhancing the processing effect of cabin low-frequency noise and harmonic noise, and also reducing the loss of local noise information. Compared with other commonly used deep networks, the proposed networks has better separation results. It not only restores a more accurate spectrum structure, but also obtain smaller distortions.
KW - acoustic signal separation
KW - cabin noise
KW - deep networks
KW - parallel dilated convolution
UR - http://www.scopus.com/inward/record.url?scp=85184824117&partnerID=8YFLogxK
U2 - 10.1109/ICICSP59554.2023.10390600
DO - 10.1109/ICICSP59554.2023.10390600
M3 - 会议稿件
AN - SCOPUS:85184824117
T3 - 2023 6th International Conference on Information Communication and Signal Processing, ICICSP 2023
SP - 417
EP - 423
BT - 2023 6th International Conference on Information Communication and Signal Processing, ICICSP 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th International Conference on Information Communication and Signal Processing, ICICSP 2023
Y2 - 23 September 2023 through 25 September 2023
ER -