Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection

arXiv cs.AISeptember 7, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2609.04561v1 Announce Type: new Abstract: Whisper is a widely used foundation model for automatic speech recognition (ASR), but its generative decoder can produce fluent hallucinated transcripts for inputs containing little or no speech. We propose a training-free, inference-time method to reduce these hallucinations using low-rank projection of decoder activations. A compact hallucination-associated subspace is estimated from non-speech calibration data, and decoder hidden states are projected away from this subspace during inference. We evaluate two variants: always-on, which applies projection to all inputs, and gated, which applies it only when Whisper predicts that an input is lik

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Röst-AI
• Verktyg
• Forskning