Signals 4 · free daily AI digest

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 →

#4 most recent of 252 cs.CL papers we have recorded · ↑ newer: ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimin · ↓ older: Screen Before You Serve: Simulation for Production Customer Experience
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
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions