تقرير
FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching
| العنوان: | FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching |
|---|---|
| المؤلفون: | Jung, Chaeyoung, Lee, Suyeon, Kim, Ji-Hoon, Chung, Joon Son |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound |
| الوصف: | 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.ioTest/ Comment: INTERSPEECH 2024 |
| نوع الوثيقة: | Working Paper |
| الوصول الحر: | http://arxiv.org/abs/2406.09286Test |
| رقم الانضمام: | edsarx.2406.09286 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |