B-GRPO：基于批量-组相对策略优化的无监督语音情绪识别
B-GRPO: Unsupervised Speech Emotion Recognition based on Batched-Group Relative Policy Optimization
AI总结：
B-GRPO通过引入自我奖励和教师奖励函数，改进组相对策略优化方法，提升无监督语音情绪识别的性能。
摘要：
无监督语音情绪识别（SER）聚焦于解决情感语音的数据稀疏性和标注偏差问题。强化学习（RL）是一种有前景的方法，通过规则基于或模型基于的验证函数来提升性能，而不是依赖人工标注。我们将学习过程中的样本选择视为一个长期过程，是否选择样本作为动作来制定策略，从而实现将RL应用于SER中测量样本质量。我们提出了一种改进的组相对策略优化（GRPO），以适应分类问题，将批量中的样本视为一组，并使用这些样本的平均奖励作为基准来计算优势。与GRPO中使用的可验证奖励函数不同，我们提出了自我奖励函数和教师奖励函数，以鼓励模型生成高置信度的输出。实验表明，所提出的方法在无RL基线的情况下将性能提高了19.8%。
英文摘要：
Unsupervised speech emotion recognition (SER) focuses on addressing the problem of data sparsity and annotation bias of emotional speech. Reinforcement learning (RL) is a promising method which enhances the performance through rule-based or model-based verification functions rather than human annotations. We treat the sample selection during the learning process as a long-term procedure and whether to select a sample as the action to make policy, thus achieving the application of RL to measure sample quality in SER. We propose a modified Group Relative Policy Optimization (GRPO) to adapt it to classification problems, which takes the samples in a batch as a group and uses the average reward of these samples as the baseline to calculate the advantage. And rather than using a verifiable reward function as in GRPO, we put forward self-reward functions and teacher-reward functions to encourage the model to produce high-confidence outputs. Experiments indicate that the proposed method improves the performance of baseline without RL by 19.8%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
