用情境化象形图修复多语言 ASR 错误

Contextual Pictograms for Repairing Multilingual ASR Errors

AI 导读

一个结合备选转写、重放与情境化象形图的界面被提出，用于修复多语言 ASR 错误，初期支持法语和西班牙语的功能性话语。该系统将开展平衡实验，评估图像反馈能否在纯文本备选之外帮助听者还原说话人意图，并量化语义偏差与额外交互时间。

正文 · 原文

Abstract:Speech transcription errors can be difficult to recognize when competing word hypotheses are unfamiliar or visually similar. We describe an interface that combines alternative transcripts, replay and contextually checked pictograms for selected uncertain concepts. The system will initially support French and Spanish functional utterances. A counterbalanced study will assess whether pictorial feedback helps listeners recover the speaker's intended action beyond text alternatives alone. We will also quantify semantic mismatch and additional interaction time, since an inappropriate image can reinforce the wrong interpretation rather than repair it.

Subjects:	Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
Cite as:	arXiv:2611.05637 [cs.CL]
	(or arXiv:2611.05637v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2611.05637 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Carlos Bruno [view email]
[v1] Tue, 3 Nov 2026 21:21:18 UTC (274 KB)

来源：arXiv cs.CL · arxiv.org