A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition
Paper recorded by Signals 4 on 2026-09-24 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-24 on arXiv · recorded by Signals 4 on 2026-09-25
Category: cs.CL · 自然语言处理 · first seen 2026-09-25
Abstract
Automatic speech recognition is typically trained assuming that the reference transcript is the only valid labeling of an utterance, yet even nominally verbatim transcripts contain localized differences in pronunciation, spelling, or lexical realization that the acoustics do not uniquely determine. Omni-temporal Classification (OTC) tolerates such noise by adding wildcard paths to the connectionis
Read on arXiv →
Cite this page: A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition: the #4 most recent of 252 cs.CL papers we have recorded (as of 2026-09-24). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/a-training-criterion-with-token-level-tolerance-to-transcription-ambiguity-for-a.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free