BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916238106558464 |
|---|---|
| author | Moliner, Eloi Lemercier, Jean-Marie Welker, Simon Gerkmann, Timo Välimäki, Vesa |
| author_facet | Moliner, Eloi Lemercier, Jean-Marie Welker, Simon Gerkmann, Timo Välimäki, Vesa |
| contents | In this paper, we present an unsupervised single-channel method for joint blind dereverberation and room impulse response estimation, based on posterior sampling with diffusion models. We parameterize the reverberation operator using a filter with exponential decay for each frequency subband, and iteratively estimate the corresponding parameters as the speech utterance gets refined along the reverse diffusion trajectory. A measurement consistency criterion enforces the fidelity of the generated speech with the reverberant measurement, while an unconditional diffusion model implements a strong prior for clean speech generation. Without any knowledge of the room impulse response nor any coupled reverberant-anechoic data, we can successfully perform dereverberation in various acoustic scenarios. Our method significantly outperforms previous blind unsupervised baselines, and we demonstrate its increased robustness to unseen acoustic conditions in comparison to blind supervised methods. Audio samples and code are available online. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_04272 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models Moliner, Eloi Lemercier, Jean-Marie Welker, Simon Gerkmann, Timo Välimäki, Vesa Audio and Speech Processing Machine Learning Sound In this paper, we present an unsupervised single-channel method for joint blind dereverberation and room impulse response estimation, based on posterior sampling with diffusion models. We parameterize the reverberation operator using a filter with exponential decay for each frequency subband, and iteratively estimate the corresponding parameters as the speech utterance gets refined along the reverse diffusion trajectory. A measurement consistency criterion enforces the fidelity of the generated speech with the reverberant measurement, while an unconditional diffusion model implements a strong prior for clean speech generation. Without any knowledge of the room impulse response nor any coupled reverberant-anechoic data, we can successfully perform dereverberation in various acoustic scenarios. Our method significantly outperforms previous blind unsupervised baselines, and we demonstrate its increased robustness to unseen acoustic conditions in comparison to blind supervised methods. Audio samples and code are available online. |
| title | BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2405.04272 |