Xiaolin Hu

Papers that credit Xiaolin Hu in their source bylines. Matching names may refer to different researchers.

1 results

1. PaperAudio & Speech

   A broader speech test and a single-pass extractor

   RealSSA tests varied audio-visual speech scenes, while Falcon’s separation score on its simulated test set slightly exceeds a causal baseline.

   Added to Chiosa Oct 29, 2026