Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2309.13874 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914964866859008 |
|---|---|
| author | Zhang, Leying Qian, Yao Yu, Linfeng Wang, Heming Yang, Hemin Zhou, Long Liu, Shujie Qian, Yanmin |
| author_facet | Zhang, Leying Qian, Yao Yu, Linfeng Wang, Heming Yang, Hemin Zhou, Long Liu, Shujie Qian, Yanmin |
| contents | Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction under multi-speaker noisy conditions remains relatively unexplored. Moreover, the superior quality of diffusion methods typically comes at the cost of slower inference speed. In this paper, we introduce the Discriminative Diffusion model for Target Speech Extraction (DDTSE). We apply the same forward process as diffusion models and utilize the reconstruction loss similar to discriminative methods. Furthermore, we devise a two-stage training strategy to emulate the inference process during model training. DDTSE not only works as a standalone system, but also can further improve the performance of discriminative models without additional retraining. Experimental results demonstrate that DDTSE not only achieves higher perceptual quality but also accelerates the inference process by 3 times compared to the conventional diffusion model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_13874 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DDTSE: Discriminative Diffusion Model for Target Speech Extraction Zhang, Leying Qian, Yao Yu, Linfeng Wang, Heming Yang, Hemin Zhou, Long Liu, Shujie Qian, Yanmin Audio and Speech Processing Machine Learning Sound Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction under multi-speaker noisy conditions remains relatively unexplored. Moreover, the superior quality of diffusion methods typically comes at the cost of slower inference speed. In this paper, we introduce the Discriminative Diffusion model for Target Speech Extraction (DDTSE). We apply the same forward process as diffusion models and utilize the reconstruction loss similar to discriminative methods. Furthermore, we devise a two-stage training strategy to emulate the inference process during model training. DDTSE not only works as a standalone system, but also can further improve the performance of discriminative models without additional retraining. Experimental results demonstrate that DDTSE not only achieves higher perceptual quality but also accelerates the inference process by 3 times compared to the conventional diffusion model. |
| title | DDTSE: Discriminative Diffusion Model for Target Speech Extraction |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2309.13874 |