从非平衡语音数据中学习情感表征以用于语音情感识别与情感文本转语音
Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech
AI总结：
针对情感语音数据集不平衡易致模型过拟合的问题，提出结合增强方法的Emotion Extractor，可提取有效泛化的情感表征，在SER任务上超越SOTA基线，还能提升情感TTS的语音表现力。
摘要：
有效的语音情感表征在语音情感识别（SER）和情感文本转语音（TTS）任务中发挥着关键作用。然而，与中性风格语音相比，情感语音样本的获取难度更大、成本更高，这导致了大多数相关研究都不幸忽略的一个问题：数据集不平衡。模型可能会对占多数的中性类别过拟合，无法生成鲁棒且有效的情感表征。在本文中，我们提出了一种Emotion Extractor（情感提取器）来解决这一问题。我们采用增强方法训练模型，使其能够从非平衡数据集中提取有效且具备泛化性的情感表征。我们的实验结果表明：（1）在SER任务上，所提出的Emotion Extractor在三个非平衡数据集上均超越了当前最优基线；（2）我们的Emotion Extractor生成的表征对TTS模型有助益，使其能够合成更具表现力的语音。
英文摘要：
Effective speech emotional representations play a key role in Speech Emotion Recognition (SER) and Emotional Text-To-Speech (TTS) tasks. However, emotional speech samples are more difficult and expensive to acquire compared with Neutral style speech, which causes one issue that most related works unfortunately neglect: imbalanced datasets. Models might overfit to the majority Neutral class and fail to produce robust and effective emotional representations. In this paper, we propose an Emotion Extractor to address this issue. We use augmentation approaches to train the model and enable it to extract effective and generalizable emotional representations from imbalanced datasets. Our empirical results show that (1) for the SER task, the proposed Emotion Extractor surpasses the state-of-the-art baseline on three imbalanced datasets; (2) the produced representations from our Emotion Extractor benefit the TTS model, and enable it to synthesize more expressive speech.
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。
