_akhaliq· @_akhaliq · X·· 12 小时前AI 评分
高效流式视听目标说话人提取论文
面向真实世界声学场景的高效流式视听目标说话人提取 论文:huggingface.co/papers/2610.3…
Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes
paper: huggingface.co/papers/2610.3…
来源:_akhaliq · x.com