AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models

Excerpt

arXiv:2609.23979v1 Announce Type: cross Abstract: Attention encoder-decoder (AED) Speech Foundation Models achieve strong ASR performance but can generate acoustically unsupported text when inputs contain no speech, weak acoustic evidence, or unreliable transcription. We propose AURA: Activation-editing with Uncertainty-Routed Adaptation, an ultra-efficient representation-editing method that freezes the pretrained model and applies sparse scale-and-shift edits to decoder cross-attention heads. A