AI speech-to-text can hallucinate violent language
Source evidence cited by public records. This page shows where the source is used, its trust tier, and when it was last checked in the seed.
Records using this source
- Whisper Speech-to-Text AI Reportedly Found to Create Violent Hallucinations
event | 17 June 2024 | 78%
Researchers at Cornell reportedly found that OpenAI's Whisper, a speech-to-text system, can hallucinate violent language and fabricated details, especially with long pauses in speech, such as from those with speech impairments. Analyzing 13,000 clips, they determined 1% contained harmful hallucinations. These errors pose risks in hiring, legal trials, and medical documentation. The study suggests improving model training to reduce these hallucinations for diverse speaking pa…