FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917693049798656 |
|---|---|
| author | Jung, Chaeyoung Lee, Suyeon Kim, Ji-Hoon Chung, Joon Son |
| author_facet | Jung, Chaeyoung Lee, Suyeon Kim, Ji-Hoon Chung, Joon Son |
| contents | This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is limited by slow inference speeds and computational complexity. To address this issue, we present FlowAVSE which enhances the inference speed and reduces the number of learnable parameters without degrading the output quality. In particular, we employ a conditional flow matching algorithm that enables the generation of high-quality speech in a single sampling step. Moreover, we increase efficiency by optimizing the underlying U-net architecture of diffusion-based systems. Our experiments demonstrate that FlowAVSE achieves 22 times faster inference speed and reduces the model size by half while maintaining the output quality. The demo page is available at: https://cyongong.github.io/FlowAVSE.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09286 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching Jung, Chaeyoung Lee, Suyeon Kim, Ji-Hoon Chung, Joon Son Audio and Speech Processing Sound This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is limited by slow inference speeds and computational complexity. To address this issue, we present FlowAVSE which enhances the inference speed and reduces the number of learnable parameters without degrading the output quality. In particular, we employ a conditional flow matching algorithm that enables the generation of high-quality speech in a single sampling step. Moreover, we increase efficiency by optimizing the underlying U-net architecture of diffusion-based systems. Our experiments demonstrate that FlowAVSE achieves 22 times faster inference speed and reduces the model size by half while maintaining the output quality. The demo page is available at: https://cyongong.github.io/FlowAVSE.github.io/ |
| title | FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2406.09286 |