Matching Reverberant Speech Through Learned Acoustic Embeddings and Feedback Delay Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911234551447552 |
|---|---|
| author | Götz, Philipp Santo, Gloria Dal Schlecht, Sebastian J. Välimäki, Vesa Habets, Emanuël A. P. |
| author_facet | Götz, Philipp Santo, Gloria Dal Schlecht, Sebastian J. Välimäki, Vesa Habets, Emanuël A. P. |
| contents | Reverberation conveys critical acoustic cues about the environment, supporting spatial awareness and immersion. For auditory augmented reality (AAR) systems, generating perceptually plausible reverberation in real time remains a key challenge, especially when explicit acoustic measurements are unavailable. We address this by formulating blind estimation of artificial reverberation parameters as a reverberant signal matching task, leveraging a learned room-acoustic prior. Furthermore, we propose a feedback delay network (FDN) structure that reproduces both frequency-dependent decay times and the direct-to-reverberation ratio of a target space. Experimental evaluation against a leading automatic FDN tuning method demonstrates improvements in estimated room-acoustic parameters and perceptual plausibility of artificial reverberant speech. These results highlight the potential of our approach for efficient, perceptually consistent reverberation rendering in AAR applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23158 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Matching Reverberant Speech Through Learned Acoustic Embeddings and Feedback Delay Networks Götz, Philipp Santo, Gloria Dal Schlecht, Sebastian J. Välimäki, Vesa Habets, Emanuël A. P. Audio and Speech Processing Reverberation conveys critical acoustic cues about the environment, supporting spatial awareness and immersion. For auditory augmented reality (AAR) systems, generating perceptually plausible reverberation in real time remains a key challenge, especially when explicit acoustic measurements are unavailable. We address this by formulating blind estimation of artificial reverberation parameters as a reverberant signal matching task, leveraging a learned room-acoustic prior. Furthermore, we propose a feedback delay network (FDN) structure that reproduces both frequency-dependent decay times and the direct-to-reverberation ratio of a target space. Experimental evaluation against a leading automatic FDN tuning method demonstrates improvements in estimated room-acoustic parameters and perceptual plausibility of artificial reverberant speech. These results highlight the potential of our approach for efficient, perceptually consistent reverberation rendering in AAR applications. |
| title | Matching Reverberant Speech Through Learned Acoustic Embeddings and Feedback Delay Networks |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.23158 |