Emotions lie on a continuum, but current models treat emotions as a finite
valued discrete variable. This representation does not capture the diversity in
the expression of emotion. To better represent emotions we propose the use of
natural language descriptions (or prompts). In this work, we address the
challenge of automatically generating these prompts and training a model to
better learn emotion representations from audio and prompt pairs. We use
acoustic properties that are correlated to emotion like pitch, intensity,
speech rate, and articulation rate to automatically generate prompts i.e.
'acoustic prompts'. We use a contrastive learning objective to map speech to
their respective acoustic prompts. We evaluate our model on Emotion Audio
Retrieval and Speech Emotion Recognition. Our results show that the acoustic
prompts significantly improve the model's performance in EAR, in various
Precision@K metrics. In SER, we observe a 3.8% relative accuracy improvement on
the Ravdess dataset.

通过使用自然语言描述和基于声学特性的提示来更好地表示情绪的表达，我们提出了一种方法来自动生成这些提示并训练模型从音频和提示的组合中更好地学习情绪表示。使用声调、强度、说话速度和发音速度等与情绪相关的声学特性自动生成 ' 声学提示 '，通过对比学习目标将语音映射到相应的声学提示。我们在情绪音频检索和语音情绪识别上评估了我们的模型。结果表明，声学提示显著改善了模型在 EAR 中的性能，特别是在各种 Precision@K 指标上。在 Ravdess 数据集上，我们观察到 SER 的相对准确率提高了 3.8%。