Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2505.22051 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912416982368256 |
|---|---|
| author | Shen, Pengjie Zhang, Xueliang Wang, Zhong-Qiu |
| author_facet | Shen, Pengjie Zhang, Xueliang Wang, Zhong-Qiu |
| contents | We propose ARiSE, an auto-regressive algorithm for multi-channel speech enhancement. ARiSE improves existing deep neural network (DNN) based frame-online multi-channel speech enhancement models by introducing auto-regressive connections, where the estimated target speech at previous frames is leveraged as extra input features to help the DNN estimate the target speech at the current frame. The extra input features can be derived from (a) the estimated target speech in previous frames; and (b) a beamformed mixture with the beamformer computed based on the previous estimated target speech. On the other hand, naively training the DNN in an auto-regressive manner is very slow. To deal with this, we propose a parallel training mechanism to speed up the training. Evaluation results in noisy-reverberant conditions show the effectiveness and potential of the proposed algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22051 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ARiSE: Auto-Regressive Multi-Channel Speech Enhancement Shen, Pengjie Zhang, Xueliang Wang, Zhong-Qiu Audio and Speech Processing We propose ARiSE, an auto-regressive algorithm for multi-channel speech enhancement. ARiSE improves existing deep neural network (DNN) based frame-online multi-channel speech enhancement models by introducing auto-regressive connections, where the estimated target speech at previous frames is leveraged as extra input features to help the DNN estimate the target speech at the current frame. The extra input features can be derived from (a) the estimated target speech in previous frames; and (b) a beamformed mixture with the beamformer computed based on the previous estimated target speech. On the other hand, naively training the DNN in an auto-regressive manner is very slow. To deal with this, we propose a parallel training mechanism to speed up the training. Evaluation results in noisy-reverberant conditions show the effectiveness and potential of the proposed algorithms. |
| title | ARiSE: Auto-Regressive Multi-Channel Speech Enhancement |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.22051 |