{"ID":2863954,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25458","arxiv_id":"2509.25458","title":"Plug-and-Play Emotion Graphs for Compositional Prompting in Zero-Shot Speech Emotion Recognition","abstract":"Large audio-language models (LALMs) exhibit strong zero-shot performance across speech tasks but struggle with speech emotion recognition (SER) due to weak paralinguistic modeling and limited cross-modal reasoning. We propose Compositional Chain-of-Thought Prompting for Emotion Reasoning (CCoT-Emo), a framework that introduces structured Emotion Graphs (EGs) to guide LALMs in emotion inference without fine-tuning. Each EG encodes seven acoustic features (e.g., pitch, speech rate, jitter, shimmer), textual sentiment, keywords, and cross-modal associations. Embedded into prompts, EGs provide interpretable and compositional representations that enhance LALM reasoning. Experiments across SER benchmarks show that CCoT-Emo outperforms prior SOTA and improves accuracy over zero-shot baselines.","short_abstract":"Large audio-language models (LALMs) exhibit strong zero-shot performance across speech tasks but struggle with speech emotion recognition (SER) due to weak paralinguistic modeling and limited cross-modal reasoning. We propose Compositional Chain-of-Thought Prompting for Emotion Reasoning (CCoT-Emo), a framework that in...","url_abs":"https://arxiv.org/abs/2509.25458","url_pdf":"https://arxiv.org/pdf/2509.25458v2","authors":"[\"Jiacheng Shi\",\"Hongfei Du\",\"Y. Alicia Hong\",\"Ye Gao\"]","published":"2025-09-29T20:06:03Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}