CST: Complex Sparse Transformer for Low-SNR Speech Enhancement

Speech enhancement tasks for audio with a low SNR are challenging. Existing speech enhancement methods are mainly designed for high SNR audio, and they usually use RNNs to model audio sequence features, which causes the model to be unable to learn long-distance dependencies, thus limiting its perfor...

Descripción completa

Detalles Bibliográficos
Autores principales: Tan, Kaijun, Mao, Wenyu, Guo, Xiaozhou, Lu, Huaxiang, Zhang, Chi, Cao, Zhanzhong, Wang, Xingang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007472/
https://www.ncbi.nlm.nih.gov/pubmed/36904579
http://dx.doi.org/10.3390/s23052376

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10007472/
https://www.ncbi.nlm.nih.gov/pubmed/36904579
http://dx.doi.org/10.3390/s23052376

Ejemplares similares