Subjective feedback-based neural network pruning for speech enhancement

Ye，Fuqiang1; Tsao，Yu2; Chen，Fei1

10.1109/APSIPAASC47483.2019.9023330

2019-11-01

2309-9402

978-1-7281-3249-5

2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019

673-677

18-21 Nov. 2019

Lanzhou, China

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Speech enhancement based on neural networks provides performance superior to that of conventional algorithms. However, the network may suffer owing to redundant parameters, which demands large unnecessary computation and power consumption. This work aimed to prune the large network by removing extra neurons and connections while maintaining speech enhancement performance. Iterative network pruning combined with network retraining was employed to compress the network based on the weight magnitude of neurons and connections. This pruning method was evaluated using a deep denoising autoencoder neural network, which was trained to enhance speech perception under nonstationary noise interference. Word correct rate was utilized as the subjective intelligibility feedback to evaluate the understanding of noisy speech enhanced by the sparse network. Results showed that the iterative pruning method combined with retraining could reduce 50% of the parameters without significantly affecting the speech enhancement performance, which was superior to the two baseline conditions of direct network pruning with network retraining and iterative network pruning without network retraining. Finally, an optimized network pruning method was proposed to implement the iterative network pruning and retraining in a greedy repetition manner, yielding a maximum pruning ratio of 80%.

Speech enhancement Iterative methods Noise measurement Speech recognition Biological neural networks Indexes

第一 ; 通讯

英语

CPCI-S ; EI

Research Foundation of Department of Science and Technology of Guangdong Province[2018A050501001] ; Shenzhen High-level Overseas Talent Program[KQJSCX20180319114453986]

Computer Science ; Engineering ; Imaging Science & Photographic Technology

Computer Science, Software Engineering ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology

WOS:000555696900114

20201308362158

Speech intelligibility ; Iterative methods

Speech:751.5 ; Numerical Methods:921.6

2-s2.0-85082381842

Scopus

1.Southern University of Science and Technology,Department of Electrical and Electronic Engineering,China
2.Research Center for Information Technology Innovation,Academic Sinica,China

Ye，Fuqiang,Tsao，Yu,Chen，Fei. Subjective feedback-based neural network pruning for speech enhancement[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2019:673-677.