← Search

Haoyuan Yu

2 accepted papers

2025

Egocentric Speaker Diarization with Vision-Guided Clustering and Adaptive Speech Re-detection

ICASSP 2025accepted

Speaker diarization aims to identify "who spoke when" in multi-person conversational scenarios. State-of-the-art audio-only diarization methods divide the task into multi-stages of speech segmentation, neural speaker embedding and unsupervised clustering. Egocentric speaker diarization (i.e., diariz…

Cited by 0SourceScholar
Haoyuan Yu — accepted AI-conference papers · AIConfPaper