Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.04368 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915373395214336 |
|---|---|
| author | Zhang, Qiquan Chen, Moran Song, Zeyang Liu, Hexin Zhang, Xiangyu Li, Haizhou |
| author_facet | Zhang, Qiquan Chen, Moran Song, Zeyang Liu, Hexin Zhang, Xiangyu Li, Haizhou |
| contents | Advanced long-context modeling backbone networks, such as Transformer, Conformer, and Mamba, have demonstrated state-of-the-art performance in speech enhancement. However, a systematic and comprehensive comparative study of these backbones within a unified speech enhancement framework remains lacking. In addition, xLSTM, a more recent and efficient variant of LSTM, has shown promising results in language modeling and as a general-purpose vision backbone. In this paper, we investigate the capability of xLSTM in speech enhancement, and conduct a comprehensive comparison and analysis of the Transformer, Conformer, Mamba, and xLSTM backbones within a unified framework, considering both causal and noncausal configurations. Overall, xLSTM and Mamba achieve better performance than Transformer and Conformer. Mamba demonstrates significantly superior training and inference efficiency, particularly for long speech inputs, whereas xLSTM suffers from the slowest processing speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04368 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study Zhang, Qiquan Chen, Moran Song, Zeyang Liu, Hexin Zhang, Xiangyu Li, Haizhou Audio and Speech Processing Advanced long-context modeling backbone networks, such as Transformer, Conformer, and Mamba, have demonstrated state-of-the-art performance in speech enhancement. However, a systematic and comprehensive comparative study of these backbones within a unified speech enhancement framework remains lacking. In addition, xLSTM, a more recent and efficient variant of LSTM, has shown promising results in language modeling and as a general-purpose vision backbone. In this paper, we investigate the capability of xLSTM in speech enhancement, and conduct a comprehensive comparison and analysis of the Transformer, Conformer, Mamba, and xLSTM backbones within a unified framework, considering both causal and noncausal configurations. Overall, xLSTM and Mamba achieve better performance than Transformer and Conformer. Mamba demonstrates significantly superior training and inference efficiency, particularly for long speech inputs, whereas xLSTM suffers from the slowest processing speed. |
| title | Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2507.04368 |