Speech dereverberation constrained on room impulse response characteristics
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909250918285312 |
|---|---|
| author | Bahrman, Louis Fontaine, Mathieu Roux, Jonathan Le Richard, Gaël |
| author_facet | Bahrman, Louis Fontaine, Mathieu Roux, Jonathan Le Richard, Gaël |
| contents | Single-channel speech dereverberation aims at extracting a dry speech signal from a recording affected by the acoustic reflections in a room. However, most current deep learning-based approaches for speech dereverberation are not interpretable for room acoustics, and can be considered as black-box systems in that regard. In this work, we address this problem by regularizing the training loss using a novel physical coherence loss which encourages the room impulse response (RIR) induced by the dereverberated output of the model to match the acoustic properties of the room in which the signal was recorded. Our investigation demonstrates the preservation of the original dereverberated signal alongside the provision of a more physically coherent RIR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08657 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Speech dereverberation constrained on room impulse response characteristics Bahrman, Louis Fontaine, Mathieu Roux, Jonathan Le Richard, Gaël Sound Audio and Speech Processing Signal Processing Single-channel speech dereverberation aims at extracting a dry speech signal from a recording affected by the acoustic reflections in a room. However, most current deep learning-based approaches for speech dereverberation are not interpretable for room acoustics, and can be considered as black-box systems in that regard. In this work, we address this problem by regularizing the training loss using a novel physical coherence loss which encourages the room impulse response (RIR) induced by the dereverberated output of the model to match the acoustic properties of the room in which the signal was recorded. Our investigation demonstrates the preservation of the original dereverberated signal alongside the provision of a more physically coherent RIR. |
| title | Speech dereverberation constrained on room impulse response characteristics |
| topic | Sound Audio and Speech Processing Signal Processing |
| url | https://arxiv.org/abs/2407.08657 |