Do We Still Need Audio? Rethinking Speaker Diarization with a Text-Based Approach Using Multiple Prediction Models | OpenReview

Do We Still Need Audio? Rethinking Speaker Diarization with a Text-Based Approach Using Multiple Prediction Models

Open Webpage

Peilin Wu, Jinho D. Choi

Published: 2025, Last Modified: 08 Jan 2026CoRR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0

External IDs:dblp:journals/corr/abs-2506-11344

Loading