Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation
Kevin Miller, Arjun Chandra, Venkatesh Saligrama
Audio-language models (ALMs) are increasingly used as judges for speech-to-speech systems, but a judge that receives audio may not actually use paralinguistic evidence. We introduc…
cs.CL2026
Hearing Between the Lines: Unlocking the Reasoning Power of LLMs for Speech Evaluation
Arjun Chandra, Kevin Miller, Venkatesh Ravichandran +2
Large Language Model (LLM) judges exhibit strong reasoning capabilities but are limited to textual content. This leaves current automatic Speech-to-Speech (S2S) evaluation methods…