无心的低语：语音转文本幻觉的危害
Careless Whisper: Speech-to-Text Hallucination Harms
AI总结：
本文评估Whisper语音转文本服务，发现约1%的转写包含幻觉内容，其中38%涉及明确危害，且幻觉在失语症说话者中不成比例出现，呼吁行业改善幻觉问题并关注下游偏见。
摘要：
语音转文本服务旨在尽可能准确地将输入音频转写为文字。它们在日常生活中扮演着越来越重要的角色，例如用于个人语音助手或客户与公司之间的互动。我们评估了OpenAI的Whisper，这是一项截至2023年超越行业竞争对手的最先进自动语音识别服务。虽然Whisper的许多转写结果高度准确，但我们发现大约1%的音频转写包含完整的幻觉短语或句子，这些内容在底层音频中不存在任何形式。我们对Whisper幻觉内容进行了主题分析，发现38%的幻觉包含明确危害，例如延续暴力、编造不准确的关联或暗示虚假权威。随后，我们通过观察失语症说话者（他们使用言语和声音表达自己的能力降低）与对照组之间幻觉率的差异来研究幻觉产生的原因。我们发现，幻觉不成比例地出现在那些非发声时长占比较高的个体中——这是失语症的常见症状。我们呼吁行业从业者改善Whisper中这些基于语言模型的幻觉，并提高对语音转文本模型下游应用中因幻觉而放大的潜在偏见的认识。
英文摘要：
Speech-to-text services aim to transcribe input audio as accurately as possible. They increasingly play a role in everyday life, for example in personal voice assistants or in customer-company interactions. We evaluate Open AI's Whisper, a state-of-the-art automated speech recognition service outperforming industry competitors, as of 2023. While many of Whisper's transcriptions were highly accurate, we find that roughly 1\% of audio transcriptions contained entire hallucinated phrases or sentences which did not exist in any form in the underlying audio. We thematically analyze the Whisper-hallucinated content, finding that 38\% of hallucinations include explicit harms such as perpetuating violence, making up inaccurate associations, or implying false authority. We then study why hallucinations occur by observing the disparities in hallucination rates between speakers with aphasia (who have a lowered ability to express themselves using speech and voice) and a control group. We find that hallucinations disproportionately occur for individuals who speak with longer shares of non-vocal durations -- a common symptom of aphasia. We call on industry practitioners to ameliorate these language-model-based hallucinations in Whisper, and to raise awareness of potential biases amplified by hallucinations in downstream applications of speech-to-text models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
