DiEmo-TTS：通过自监督蒸馏实现语音合成中跨说话人情感迁移的解耦情感表征
DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech
AI总结：
提出DiEmo-TTS，通过自监督蒸馏和聚类匹配学习说话人无关的情感嵌入，实现跨说话人情感迁移，减少说话人泄漏并提升合成质量。
摘要：
语音合成中的跨说话人情感迁移依赖于提取与说话人无关的情感嵌入，以实现准确的情感建模，同时不保留说话人特征。然而，现有的音色压缩方法未能完全分离说话人和情感特征，导致说话人泄漏和合成质量下降。为解决这一问题，我们提出了DiEmo-TTS，一种自监督蒸馏方法，以最小化情感信息损失并保留说话人身份。我们引入了聚类驱动采样和信息扰动来保留情感，同时去除不相关因素。为促进这一过程，我们提出了一种使用情感属性预测和说话人嵌入的情感聚类与匹配方法，使其能够泛化到未标记数据。此外，我们设计了一个双条件Transformer以更好地整合风格特征。实验结果证实了我们的方法在学习与说话人无关的情感嵌入方面的有效性。
英文摘要：
Cross-speaker emotion transfer in speech synthesis relies on extracting speaker-independent emotion embeddings for accurate emotion modeling without retaining speaker traits. However, existing timbre compression methods fail to fully separate speaker and emotion characteristics, causing speaker leakage and degraded synthesis quality. To address this, we propose DiEmo-TTS, a self-supervised distillation method to minimize emotional information loss and preserve speaker identity. We introduce cluster-driven sampling and information perturbation to preserve emotion while removing irrelevant factors. To facilitate this process, we propose an emotion clustering and matching approach using emotional attribute prediction and speaker embeddings, enabling generalization to unlabeled data. Additionally, we designed a dual conditioning transformer to integrate style features better. Experimental results confirm the effectiveness of our method in learning speaker-irrelevant emotion embeddings.
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。
