Explainable DNN-based Beamformer with Postfilter
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915024243523584 |
|---|---|
| author | Cohen, Adi Wong, Daniel Lee, Jung-Suk Gannot, Sharon |
| author_facet | Cohen, Adi Wong, Daniel Lee, Jung-Suk Gannot, Sharon |
| contents | This paper introduces an explainable DNN-based beamformer with a postfilter (ExNet-BF+PF) for multichannel signal processing. Our approach combines the U-Net network with a beamformer structure to address this problem. The method involves a two-stage processing pipeline. In the first stage, time-invariant weights are applied to construct a multichannel spatial filter, namely a beamformer. In the second stage, a time-varying single-channel post-filter is applied at the beamformer output. Additionally, we incorporate an attention mechanism inspired by its successful application in noisy and reverberant environments to improve speech enhancement further.
Furthermore, our study fills a gap in the existing literature by conducting a thorough spatial analysis of the network's performance. Specifically, we examine how the network utilizes spatial information during processing. This analysis yields valuable insights into the network's functionality, thereby enhancing our understanding of its overall performance.
Experimental results demonstrate that our approach is not only straightforward to train but also yields superior results, obviating the necessity for prior knowledge of the speaker's activity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_10854 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explainable DNN-based Beamformer with Postfilter Cohen, Adi Wong, Daniel Lee, Jung-Suk Gannot, Sharon Audio and Speech Processing This paper introduces an explainable DNN-based beamformer with a postfilter (ExNet-BF+PF) for multichannel signal processing. Our approach combines the U-Net network with a beamformer structure to address this problem. The method involves a two-stage processing pipeline. In the first stage, time-invariant weights are applied to construct a multichannel spatial filter, namely a beamformer. In the second stage, a time-varying single-channel post-filter is applied at the beamformer output. Additionally, we incorporate an attention mechanism inspired by its successful application in noisy and reverberant environments to improve speech enhancement further. Furthermore, our study fills a gap in the existing literature by conducting a thorough spatial analysis of the network's performance. Specifically, we examine how the network utilizes spatial information during processing. This analysis yields valuable insights into the network's functionality, thereby enhancing our understanding of its overall performance. Experimental results demonstrate that our approach is not only straightforward to train but also yields superior results, obviating the necessity for prior knowledge of the speaker's activity. |
| title | Explainable DNN-based Beamformer with Postfilter |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2411.10854 |