LiSenNet: Lightweight Sub-band and Dual-Path Modeling for Real-Time Speech Enhancement
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912036820090880 |
|---|---|
| author | Yan, Haoyin Zhang, Jie Fan, Cunhang Zhou, Yeping Liu, Peiqi |
| author_facet | Yan, Haoyin Zhang, Jie Fan, Cunhang Zhou, Yeping Liu, Peiqi |
| contents | Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the large computational complexity and model size heavily limit the deployment on latency-sensitive and low-resource edge devices. In this work, we propose a lightweight SE network (LiSenNet) for real-time applications. We design sub-band downsampling and upsampling blocks and a dual-path recurrent module to capture band-aware features and time-frequency patterns, respectively. A noise detector is developed to detect noisy regions in order to perform SE adaptively and save computational costs. Compared to recent higher-resource-dependent baseline models, the proposed LiSenNet can achieve a competitive performance with only 37k parameters (half of the state-of-the-art model) and 56M multiply-accumulate (MAC) operations per second. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13285 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LiSenNet: Lightweight Sub-band and Dual-Path Modeling for Real-Time Speech Enhancement Yan, Haoyin Zhang, Jie Fan, Cunhang Zhou, Yeping Liu, Peiqi Audio and Speech Processing Sound Signal Processing Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the large computational complexity and model size heavily limit the deployment on latency-sensitive and low-resource edge devices. In this work, we propose a lightweight SE network (LiSenNet) for real-time applications. We design sub-band downsampling and upsampling blocks and a dual-path recurrent module to capture band-aware features and time-frequency patterns, respectively. A noise detector is developed to detect noisy regions in order to perform SE adaptively and save computational costs. Compared to recent higher-resource-dependent baseline models, the proposed LiSenNet can achieve a competitive performance with only 37k parameters (half of the state-of-the-art model) and 56M multiply-accumulate (MAC) operations per second. |
| title | LiSenNet: Lightweight Sub-band and Dual-Path Modeling for Real-Time Speech Enhancement |
| topic | Audio and Speech Processing Sound Signal Processing |
| url | https://arxiv.org/abs/2409.13285 |