2023
doi: 10.12720/jait.14.4.694-700
Multi-speaker Speech Separation under Reverberation Conditions Using Conv-Tasnet
Chunxi Wang
,
Maoshen Jia* ,
Yanyan Zhang ,
Lu Li
- Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology Beijing University of Technology, Beijing, China
- Manuscript receivedJanuary 1, 2023
- revisedFebruary 5, 2023
- acceptedMarch 22, 2023
- publishedJuly 26, 2023
Abstract
The goal of speech separation is to separate the target signal from the background interference. With the rapid development of artificial intelligence, speech separation technology combined with deep learning has received more attention as well as a lot of progress. However, in the “cocktail party problem”, it is still a challenge to achieve speech separation under reverberant conditions. In order to solve this problem, a model combining the Weighted Prediction Error (WPE) method and a fully-convolutional time-domain audio separation network (Conv-Tasnet) is proposed in this paper. The model target on separating multi-channel signals after dereverberation without prior knowledge of the second field environment. Subjective and objective evaluation results show that the proposed method outperforms existing methods in the speech separation tasks in reverberant and anechoic environments.
Keywords
- speech separation
- deep learning
- dereverberation
- speech enhancement
How to Cite
Chunxi Wang, Maoshen Jia, Yanyan Zhang, and Lu Li, "Multi-speaker Speech Separation under Reverberation Conditions Using Conv-Tasnet," Journal of Advances in Information Technology, vol. 14, no. 4, pp. 694-700, 2023. https://doi.org/10.12720/jait.14.4.694-700
Copyright & License
Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
