arXiv (All)
open access
A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition
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.
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- SURE-Voice: A Front-End Baseline for Speech-Evidence Filtering in Speech LLMs#1084345
- Asymmetric Classifier-Free Guidance for Target-Speaker ASR#1104675
- Rethinking Human-Aligned Evaluation: An Analysis of Semantic Metrics Beyond WER#1036056
- Auditing Generative Audio Calls for Known-Task Audio-LLM Evaluatio#1083182
- LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition#433630
Record · ID 1078231
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive