This work proposes ARIA-Rubrics (Audio Reasoning Integrity Assessment), a lightweight, annotation-free gold reasoning chains, automatic and transparent framework comprising six complementary metrics that evaluate audio reasoning quality across perceptual grounding, reasoning coherence, and answer consistency.
Yu-Pei Li, Qi-Yang Sun, Mohamed Mady et al.· 0 citations
Spoken sarcasm detectors may exploit lexical content, prosody, or their interaction, yet conventional evaluation cannot reveal which cues drive their predictions. We introduce CLASH (Controlled Lexical-Acoustic Separation Harness), a bilingual counterfactual diagnostic framework that evaluates each utterance under orig...
Qi-Yang Sun, Xu-Dong Li, Yu-Pei Li et al.· 1 citation
This work proposes CONVTRAP-TN, a new architecture for audio-based kinship verification, and is the first to apply the successful transformer architecture to the task of audio-based kinship verification, and collects a custom speech dataset, ARKIN, which accurately reflects everyday recording conditions.
Qi-Yang Sun, Lan Zhang, Yu-Pei Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.