Bone-conduction Guided Multimodal Speech Enhancement with Conditional Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909994177265664 |
|---|---|
| author | Khanagha, Sina Lay, Bunlong Gerkmann, Timo |
| author_facet | Khanagha, Sina Lay, Bunlong Gerkmann, Timo |
| contents | Single-channel speech enhancement models face significant performance degradation in extremely noisy environments. While prior work has shown that complementary bone-conducted speech can guide enhancement, effective integration of this noise-immune modality remains a challenge. This paper introduces a novel multimodal speech enhancement framework that integrates bone-conduction sensors with air-conducted microphones using a conditional diffusion model. Our proposed model significantly outperforms previously established multimodal techniques and a powerful diffusion-based single-modal baseline across a wide range of acoustic conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12354 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Bone-conduction Guided Multimodal Speech Enhancement with Conditional Diffusion Models Khanagha, Sina Lay, Bunlong Gerkmann, Timo Audio and Speech Processing Machine Learning Sound Single-channel speech enhancement models face significant performance degradation in extremely noisy environments. While prior work has shown that complementary bone-conducted speech can guide enhancement, effective integration of this noise-immune modality remains a challenge. This paper introduces a novel multimodal speech enhancement framework that integrates bone-conduction sensors with air-conducted microphones using a conditional diffusion model. Our proposed model significantly outperforms previously established multimodal techniques and a powerful diffusion-based single-modal baseline across a wide range of acoustic conditions. |
| title | Bone-conduction Guided Multimodal Speech Enhancement with Conditional Diffusion Models |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2601.12354 |