ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding
This work develops ParA-LLM, a framework of 22 paralinguistic characteristics that surpasses state-of-the-art Audio LLMs like GPT-4o-Audio by 7.5% on ParA-Bench and releases ParA-Bench, a benchmark of 6,000 multiple-choice questions across speaker-speech, acoustic, and mixed categories.
Nishit Anand, Jia-Qi Su, Ke Chen et al.
· 1 citation