Dereverberation Using Binary Residual Masking with Time-Domain Consistency
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912620642041856 |
|---|---|
| author | Williams, Daniel G. |
| author_facet | Williams, Daniel G. |
| contents | Vocal dereverberation remains a challenging task in audio processing, particularly for real-time applications where both accuracy and efficiency are crucial. Traditional deep learning approaches often struggle to suppress reverberation without degrading vocal clarity, while recent methods that jointly predict magnitude and phase have significant computational cost. We propose a real-time dereverberation framework based on residual mask prediction in the short-time Fourier transform (STFT) domain. A U-Net architecture is trained to estimate a residual reverberation mask that suppresses late reflections while preserving direct speech components. A hybrid objective combining binary cross-entropy, residual magnitude reconstruction, and time-domain consistency further encourages both accurate suppression and perceptual quality. Together, these components enable low-latency dereverberation suitable for real-world speech and singing applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00356 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dereverberation Using Binary Residual Masking with Time-Domain Consistency Williams, Daniel G. Sound Audio and Speech Processing I.2.m; I.5.1 Vocal dereverberation remains a challenging task in audio processing, particularly for real-time applications where both accuracy and efficiency are crucial. Traditional deep learning approaches often struggle to suppress reverberation without degrading vocal clarity, while recent methods that jointly predict magnitude and phase have significant computational cost. We propose a real-time dereverberation framework based on residual mask prediction in the short-time Fourier transform (STFT) domain. A U-Net architecture is trained to estimate a residual reverberation mask that suppresses late reflections while preserving direct speech components. A hybrid objective combining binary cross-entropy, residual magnitude reconstruction, and time-domain consistency further encourages both accurate suppression and perceptual quality. Together, these components enable low-latency dereverberation suitable for real-world speech and singing applications. |
| title | Dereverberation Using Binary Residual Masking with Time-Domain Consistency |
| topic | Sound Audio and Speech Processing I.2.m; I.5.1 |
| url | https://arxiv.org/abs/2510.00356 |