解耦音调与咳嗽以在语音合成中保持说话人身份
Disentangling Pitch and Creak for Speaker Identity Preservation in Speech Synthesis
AI总结：
该研究通过解耦音调与咳嗽，改进语音合成中说话人身份的保持性能。
摘要：
我们介绍了一种系统，能够忠实修改咳嗽的感知语音质量，同时保持说话人的感知身份。虽然众所周知，高咳嗽概率通常与低音调相关，但需要注意的是，这是在说话人群体中观察到的属性，不一定适用于所有情况。通过在语音合成系统的训练数据集中增加一个基于条件连续归一化流的说话人操控模块，实现了音调与咳嗽的解耦。实验显示，在不同咳嗽操控强度范围内，说话人验证性能显著提高。
英文摘要：
We introduce a system capable of faithfully modifying the perceptual voice quality of creak while preserving the speaker's perceived identity. While it is well known that high creak probability is typically correlated with low pitch, it is important to note that this is a property observed on a population of speakers but does not necessarily hold across all situations. Disentanglement of pitch from creak is achieved by augmentation of the training dataset of a speech synthesis system with a speaker manipulation block based on conditional continuous normalizing flow. The experiments show greatly improved speaker verification performance over a range of creak manipulation strengths.
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。
