D. Rastogi

Measuring Local Acoustic Contribution in Speech LLMs via Word-Span Counterfactual Interventions

Correct transcription does not establish that a word depended on its local audio. We introduce the Acoustic Evidence Contribution (AEC), a word-level counterfactual measure of acoustic grounding. It is obtained from the change in reference-token log likelihood when the word's aligned acoustic span is replaced. We combi...