Speech emotion recognition (SER) is a pivotal technology for human-computer interaction systems. However, 80.77% of SER papers yield results that cannot be reproduced. We develop EMO-SUPERB, short for EMOtion Speech Universal PERformance Benchmark, which aims to enhance open-source initiatives for SER. EMO-SUPERB includes a user-friendly codebase to leverage 15 state-of-the-art speech self-supervised learning models (SSLMs) for exhaustive evaluation across six open-source SER datasets. EMO-SUPERB streamlines result sharing via an online leaderboard, fostering collaboration within a community-driven benchmark and thereby enhancing the development of SER. On average, 2.58% of annotations are annotated using natural language. SER relies on classification models and is unable to process natural languages, leading to the discarding of these valuable annotations. We prompt ChatGPT to mimic annotators, comprehend natural language annotations, and subsequently re-label the data. By utilizing labels generated by ChatGPT, we consistently achieve an average relative gain of 3.08% across all settings.

翻译：语音情感识别（SER）是人机交互系统中的关键技术。然而，80.77%的SER论文所呈现的结果无法复现。我们开发了EMO-SUPERB（EMOtional Speech Universal PERformance Benchmark的首字母缩写），旨在提升SER领域的开源举措。EMO-SUPERB包含一个用户友好的代码库，可充分利用15种最新语音自监督学习模型（SSLMs），在六个开源SER数据集上进行全面评估。EMO-SUPERB通过在线排行榜简化结果共享流程，促进社区驱动基准测试内的协作，从而推动SER的发展。平均有2.58%的标注采用自然语言形式。由于SER依赖分类模型且无法处理自然语言，导致这些有价值的标注被丢弃。我们引导ChatGPT模仿标注者理解自然语言标注，并随后对数据进行重新标注。通过使用ChatGPT生成的标签，我们在所有设置下平均获得了3.08%的相对性能提升。