verbatim-transcription

Tag

Cards List
#verbatim-transcription

Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing

arXiv cs.CL ↗ · 2026-07-22 Cached

This paper addresses the uncontrolled latent variable of transcription style in ASR models by introducing a method using coverage-aware decoder task tokens to enable controllable verbatim transcription with accurate word-level timing, achieving high disfluency detection F1 via zero-shot cross-lingual transfer.

0 favorites 0 likes
← Back to home

Submit Feedback