SASEGAN-TCN: Speech enhancement algorithm based on self-attention generative adversarial network and temporal convolutional network
Mathematical Biosciences and Engineering · 2024 · 21 (3) · 3860-3875
DOI: 10.3934/mbe.2024172 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematical Biosciences and Engineering, 2024. Verfasst von Rongchuang Lv und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information Engineering, Shanghai Dianji University, Shanghai 201306, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben.
Abstract (Originalsprache)
Traditional unsupervised speech enhancement models often have problems such as non-aggregation of input feature information, which will introduce additional noise during training, thereby reducing the quality of the speech signal. In order to solve the above problems, this paper analyzed the impact of problems such as non-aggregation of input speech feature information on its performance. Moreover, this article introduced a temporal convolutional neural network and proposed a SASEGAN-TCN speech enhancement model, which captured local features information and aggregated global feature information to improve model effect and training stability. The simulation experiment results showed that the model can achieve 2.1636 and 92.78% in perceptual evaluation of speech quality (PESQ) score and short-time objective intelligibility (STOI) on the Valentini dataset, and can accordingly reach 1.8077 and 83.54% on the THCHS30 dataset. In addition, this article used the enhanced speech data for the acoustic model to verify the recognition accuracy. The speech recognition error rate was reduced by 17.4%, which was a significant improvement compared to the baseline model experimental results.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronic Information Engineering, Shanghai Dianji University, Shanghai 201306, China.
- School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.
- Alibaba Group, Shanghai 201203, China.
Zitieren
APA
Lv, R., Chen, N., Cheng, S., Fan, G., Rao, L., Song, X., Lv, W., & Yang, D. (2024). SASEGAN-TCN: Speech enhancement algorithm based on self-attention generative adversarial network and temporal convolutional network. Mathematical Biosciences and Engineering, 21(3), 3860-3875. https://doi.org/10.3934/mbe.2024172
Vancouver
Lv R, Chen N, Cheng S, Fan G, Rao L, Song X, et al. SASEGAN-TCN: Speech enhancement algorithm based on self-attention generative adversarial network and temporal convolutional network. Mathematical Biosciences and Engineering. 2024;21(3):3860-3875. doi:10.3934/mbe.2024172
BibTeX
@article{Lv2024,
author = {Lv, Rongchuang and Chen, Niansheng and Cheng, Songlin and Fan, Guangyu and Rao, Lei and Song, Xiaoyong and Lv, Wenjing and Yang, Dingyu},
title = {SASEGAN-TCN: Speech enhancement algorithm based on self-attention generative adversarial network and temporal convolutional network},
journal = {Mathematical Biosciences and Engineering},
year = {2024},
volume = {21},
number = {3},
pages = {3860--3875},
doi = {10.3934/mbe.2024172}
}
EUVIMED