Fact · Speech recognition
A 2025 study of Whisper found that when non-speech sounds were played to the model, a set of hallucinated phrases appeared frequently.
Checked against its source on October 17, 2026
In the source's own words
“we show that there exists a set of hallucinations that appear frequently”
Investigation of Whisper ASR Hallucinations Induced by Non-Speech Audio, Mateusz Barański et al., arXiv (accepted for IEEE ICASSP 2025), 2025, Abstract.
Open the original (DOI 10.48550/arXiv.2501.11378)- What it measures
- The researchers induced hallucinations with many types of sound, then added similar sounds to real speech and measured the effect.
- What it does not show
- Based on the abstract only. The sounds are artificial test inputs, so the study shows the failure mode, not how often it happens in everyday dictation.
Source
Cited on
- Transcription: How to Turn Audio and Video Into TextTopic
- How to Transcribe Audio to TextGuide
- Meeting Transcription: How It Works and What to UseGuide
- Video to Text: Transcribe Videos and YouTubeGuide
- How Accurate Is Speech Recognition? The Real NumbersGuide
- Human vs AI Transcription: Accuracy, Cost, SpeedGuide
- Transcribe Audio With Whisper, ChatGPT or GeminiGuide
- Captions and Subtitles: Formats, Rules and ToolsGuide
- Are AI summaries of voice recordings accurate?Question
- Can word error rate be greater than 100%?Question
- How do you add automatic captions to YouTube Shorts?Question
- How do you translate a video into English subtitles?Question
- How do you turn voice notes into text with AI?Question
- Why does Whisper make up words nobody said?Question