Paper
21 December 2023 Single-channel speech separation algorithm combining attention mechanism and clustering algorithm
Xiaoqi Zhang, Yan Xu, Xuhui Zhang
Author Affiliations +
Proceedings Volume 12970, Fourth International Conference on Signal Processing and Computer Science (SPCS 2023); 129703Y (2023) https://doi.org/10.1117/12.3012193
Event: Fourth International Conference on Signal Processing and Computer Science (SPCS 2023), 2023, Guilin, China
Abstract
To improve the performance of single-channel speech separation, this paper proposes a time-domain single-channel speech model based on the attention mechanism, utilizing the SANet network and a density-based spherical fuzzy clustering algorithm. The model incorporates the attention mechanism into the TCN embedding network to enhance the focus on important features and effectively capture the long-term dependencies in speech feature data. During the testing phase, the density-based spherical fuzzy clustering algorithm is employed to compute the positions of attractors, thereby improving estimation accuracy and reducing the impact of outliers and noise on cluster centers. Experimental results demonstrate that the proposed model achieves good performance in speech separation tasks.
(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Xiaoqi Zhang, Yan Xu, and Xuhui Zhang "Single-channel speech separation algorithm combining attention mechanism and clustering algorithm", Proc. SPIE 12970, Fourth International Conference on Signal Processing and Computer Science (SPCS 2023), 129703Y (21 December 2023); https://doi.org/10.1117/12.3012193
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Education and training

Data modeling

Spherical lenses

Detection and tracking algorithms

Fuzzy logic

Matrices

Performance modeling

Back to Top