# EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning

arXiv: https://arxiv.org/abs/2601.15668 · HTML: https://mlsanity.com/paper/2601.15668/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2026.

## Built on by (most cited first, 15 of 15)

- [PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory](https://mlsanity.com/paper/2604.08000/) (2026)
- [Audio Interaction Model](https://mlsanity.com/paper/2606.05121/) (2026)
- [Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning](https://mlsanity.com/paper/2607.20166/) (2026)
- [Entropy-Aware Domain-Routed Mixture-of-Experts Speech-LLM Framework: A Case Study of Multi-Domain Child-Adult ASR](https://mlsanity.com/paper/2606.10454/) (2026)
- [HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence](https://mlsanity.com/paper/2608.26517/) (2026)
- [When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection](https://mlsanity.com/paper/2608.30204/) (2026)
- [AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models](https://mlsanity.com/paper/2610.01560/) (2026)
- [S-MARC: Causal Streaming Reasoning for Full-Duplex Conversational Behavior Modeling](https://mlsanity.com/paper/2602.11065/) (2026)
- [SarcasmMiner: A Dual-Track Post-Training Framework for Robust Audio-Visual Sarcasm Reasoning](https://mlsanity.com/paper/2603.05275/) (2026)
- [ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection](https://mlsanity.com/paper/2606.18988/) (2026)
- [Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs](https://mlsanity.com/paper/2609.17981/) (2026)
- [DSPO: Diversity-aware Subjective Policy Optimization for Robust Emotional Reasoning](https://mlsanity.com/paper/2609.36775/) (2026)
- [When Does a Spoken Agent Have Enough Evidence to Act? The PACT-SLM Contract Test](https://mlsanity.com/paper/2609.38232/) (2026)
- [From Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck Models](https://mlsanity.com/paper/2609.39453/) (2026)
- [EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning](https://mlsanity.com/paper/2610.13353/) (2026)

## Abstract (arXiv)

Emotional information in speech plays a unique role in multimodal perception. However, current Speech Large Language Models (SpeechLLMs), similar to conventional speech emotion recognition (SER) systems, still treat emotion understanding as a simple classification problem. This provides limited interpretability of predictions, while leaving the LLMs' expressive and reasoning capabilities underutilized. In this work, we take the first step to reformulate SER as a deep reasoning problem through reinforcement learning (RL). We propose EmotionThinker, which is designed to generate accurate emotion predictions with interpretable explanations grounded in fine-grained acoustic cues. To achieve this, we first construct EmotionCoT-35K, an emotional reasoning dataset with Chain-of-Thought annotations and detailed captions. Second, we observe that current SpeechLLMs exhibit weak prosody perception, whereas prosodic cues constitute fundamental signals for interpreting emotions. To address this, we develop the prosody-enhanced foundation model EmotionThinker-Base, and demonstrate that prosody enhancement improves emotion understanding. Third, we introduce Group-Relative-Policy-Optimization with Progressive-Trust-aware-Reasoning-Reward (GRPO-PTR) for RL. Different from standard GRPO, which relies only on rule-based outcome rewards, GRPO-PTR progressively introduces reasoning reward, dynamically adjusts it with a trustworthiness weight reflecting the alignment between reasoning and outcome, and evaluates the overall reasoning quality with a reward model based on multi-dimensional criteria. EmotionThinker outperforms previous state-of-the-art evaluation models both in emotion accuracy and explanation quality, advancing SER toward interpretable multimodal reasoning. Project page: https://github.com/dingdongwang/EmotionThinker