arXiv cs.CL· Sankalp Parashar, Preethi Jyothi, Sunita Sarawagi·· 12 小时前AI 评分31
PARDON：面向语音识别错误的定向澄清框架
Ask, Don't Guess: Targeted Clarification for Speech Recognition Errors
AI 导读
PARDON 是一个在线错误定位框架，用 pair-HMM 对含噪与干净音频解码做概率对齐生成软监督，训练反事实增益打分器输出 token 级分数并聚合为片段。在 70% 精度下，它比最强基线多识别最多 52% 的错误 token。定向复述在计入打断频率与复述长度的预算下，相对 WER 最多降低 24%。
正文 · 原文
Abstract:Speech recognition in real time in far-field conversational settings still incurs significant errors. Identifying potential error spans during streaming ASR permits a recourse mechanism where the speaker can be asked to repeat the affected content under cleaner acoustic conditions. We propose PARDON, a new framework for online error localization, that identifies spans likely to benefit from this intervention. Our supervision uses clean audio to estimate how the recognizer's output might change under improved acoustic conditions. We probabilistically align noisy and clean decodes using a pair-HMM to obtain soft supervision. These soft targets train a counterfactual gain scorer by combining a suite of acoustic and language features to produce token-level scores, that are further grouped into spans for targeted recourse. An LLM uses the ASR transcript of the repetition to revise only the selected span. At a precision of 70%, PARDON achieves the highest recall by identifying up to 52% more erroneous tokens compared to the strongest baseline. Targeted repetition yields relative WER reductions of up to 24% under a budget that accounts for both interruption frequency and the lengths of re-uttered spans.
| Comments: | Submitted to NAACL 2027 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.24809 [cs.CL] |
| (or arXiv:2610.24809v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.24809 arXiv-issued DOI via DataCite |
Submission history
From: Sankalp Parashar [view email]
[v1]
Sat, 17 Oct 2026 18:32:23 UTC (371 KB)
[v2]
Tue, 20 Oct 2026 05:23:43 UTC (371 KB)
来源：arXiv cs.CL · arxiv.org