English(EN) The Anatomy of an ASR Hallucination

ASR幻觉与Conformer-Large模型中的最终编码器阶段相关

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-07 04:00

研究人员在Conformer-Large自动语音识别（ASR）模型中确定了一个关键边界，在这个边界处会出现幻觉，即与音频无关的流畅文本。通过在降级条件下研究两个独立训练的模型（一个CTC和一个RNN-T），他们发现绕过最终编码器阶段会持续导致模型发散并产生幻觉的可能性。这个阶段是表示变得更紧凑，文本可被解码器读取的地方，这表明了接地识别失败的机制性先决条件。 AI

影响识别出ASR模型中的一种特定故障模式，有可能提高实际应用中的鲁棒性和准确性。

排序理由该集群包含一篇详细介绍ASR模型行为发现的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 32 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍ASR模型行为发现的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Hamees Sayed, Apoorv Singh, Kumar Aman, Akshat Mandloi · 2026-09-07 04:00

一次ASR幻觉的解剖

arXiv:2609.04404v1 Announce Type: new Abstract: ASR systems sometimes produce fluent text that is unrelated to the speech they receive. We view these hallucinations as one possible consequence of a broader grounding failure, in which the transcript is no longer adequately guided …

本文如何被排名

报道来源 [1]

一次ASR幻觉的解剖

相关实体

相关话题