ArrayDPS-Refine: Generative Refinement of Discriminative Multi-Channel Speech Enhancement
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908913337630720 |
|---|---|
| author | Xu, Zhongweiyang Pandey, Ashutosh Azcarreta, Juan Ni, Zhaoheng Parekh, Sanjeel Xu, Buye |
| author_facet | Xu, Zhongweiyang Pandey, Ashutosh Azcarreta, Juan Ni, Zhaoheng Parekh, Sanjeel Xu, Buye |
| contents | Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-linear distortions from regression-based objectives, especially under challenging environmental noise conditions. Inspired by ArrayDPS for unsupervised multi-channel source separation, we introduce ArrayDPS-Refine, a method designed to enhance the outputs of discriminative models using a clean speech diffusion prior. ArrayDPS-Refine is training-free, generative, and array-agnostic. It first estimates the noise spatial covariance matrix (SCM) from the enhanced speech produced by a discriminative model, then uses this estimated noise SCM for diffusion posterior sampling. This approach allows direct refinement of any discriminative model's output without retraining. Our results show that ArrayDPS-Refine consistently improves the performance of various discriminative models, including state-of-the-art waveform and STFT domain models. Audio demos are provided at https://xzwy.github.io/ArrayDPSRefineDemo/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24385 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ArrayDPS-Refine: Generative Refinement of Discriminative Multi-Channel Speech Enhancement Xu, Zhongweiyang Pandey, Ashutosh Azcarreta, Juan Ni, Zhaoheng Parekh, Sanjeel Xu, Buye Audio and Speech Processing Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-linear distortions from regression-based objectives, especially under challenging environmental noise conditions. Inspired by ArrayDPS for unsupervised multi-channel source separation, we introduce ArrayDPS-Refine, a method designed to enhance the outputs of discriminative models using a clean speech diffusion prior. ArrayDPS-Refine is training-free, generative, and array-agnostic. It first estimates the noise spatial covariance matrix (SCM) from the enhanced speech produced by a discriminative model, then uses this estimated noise SCM for diffusion posterior sampling. This approach allows direct refinement of any discriminative model's output without retraining. Our results show that ArrayDPS-Refine consistently improves the performance of various discriminative models, including state-of-the-art waveform and STFT domain models. Audio demos are provided at https://xzwy.github.io/ArrayDPSRefineDemo/. |
| title | ArrayDPS-Refine: Generative Refinement of Discriminative Multi-Channel Speech Enhancement |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2603.24385 |