arXiv cs.AI· Longjie Luo, Zhongshu Hou, Yuepeng Li, Gang Yang, Shidong Shang, Fan Zhou·· 2 天前AI 评分20
CF-AVSS：面向真实世界 AVSE 挑战赛的由粗到细音视频语音分离框架
CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge
AI 导读
CF-AVSS 是一个由粗到细的两阶段音视频语音分离框架，第一阶段用扩展至双同步视觉流的 SPAV-TFGridNet 生成视觉排序的粗估计，第二阶段用基于 TFGridNet 的目标说话人细化网络结合原始混合信号进一步提升质量，最后经开发集校准的融合输出。
正文 · 原文
Abstract:Audio-visual speech enhancement (AVSE) leverages visual cues to recover target speech from mixtures corrupted by reverberation, noise, and overlapping speakers. We propose a coarse-to-fine two-stage AVSE framework. In the first stage, a progressive SPAV-TFGridNet is extended to two synchronized visual streams to produce visually ordered coarse estimates by progressively suppressing interfering speech while preserving target reverberation and shared background noise. In the second stage, a TFGridNet-based target speaker refinement network takes the original mixture and both coarse estimates as input to further recover target speech and improve signal quality. The coarse and refined estimates are finally combined using development-set-calibrated fusion. On the ISCSLP 2026 Real-World AVSE Challenge, our system tied for first place on Track 1 and ranked second on Track 2 in OVRL, while achieving the lowest CER on both tracks at 12.31% and 14.79%, respectively.
| Comments: | Accepted by ISCSLP 2026 |
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.21773 [cs.SD] |
| (or arXiv:2610.21773v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21773 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhongshu Hou [view email]
[v1]
Thu, 15 Oct 2026 12:30:11 UTC (148 KB)
来源：arXiv cs.AI · arxiv.org