Whisper Speech-to-Text AI Reportedly Found to Create Violent Hallucinations

Summary

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 patterns.

Developers

• OpenAI

Deployers

• Whisper
• Organizations integrating Whisper into customer service systems
• OpenAI
• Companies using Whisper
• Whisper users

Harmed parties

• Users whose speech is misinterpreted by Whisper
• Professionals relying on accurate transcriptions
• Individuals with speech impairments
• General public
• People with disabilities