AutoCycle-VC：迈向瓶颈无关的零样本跨语言语音转换
AutoCycle-VC: Towards Bottleneck-Independent Zero-Shot Cross-Lingual Voice Conversion
AI总结：
本文提出AutoCycle-VC，一种采用循环一致性和梅尔频谱预处理的零样本语音转换系统，通过提取全局说话人表示，实现跨语言转换并提升合成质量，超越现有最先进方法。
摘要：
本文提出了一种具有循环结构和梅尔频谱预处理的简单且鲁棒的零样本语音转换系统。以往的工作因依赖精心设计的瓶颈结构而遭受信息损失和合成质量不佳的问题。此外，仅依赖自重建损失的模型在重现不同说话人的声音方面存在困难。为解决这些问题，我们提出了一种循环一致性损失，该损失考虑了目标说话人与源说话人之间的来回转换。此外，在说话人编码器训练期间，利用堆叠的随机打乱梅尔频谱和标签平滑方法，从语音中提取与时间无关的全局说话人表示，这是零样本转换的关键。我们的模型在主观和客观评估中均优于现有的最先进结果。此外，它促进了跨语言语音转换，并提高了合成语音的质量。
英文摘要：
This paper proposes a simple and robust zero-shot voice conversion system with a cycle structure and mel-spectrogram pre-processing. Previous works suffer from information loss and poor synthesis quality due to their reliance on a carefully designed bottleneck structure. Moreover, models relying solely on self-reconstruction loss struggled with reproducing different speakers' voices. To address these issues, we suggested a cycle-consistency loss that considers conversion back and forth between target and source speakers. Additionally, stacked random-shuffled mel-spectrograms and a label smoothing method are utilized during speaker encoder training to extract a time-independent global speaker representation from speech, which is the key to a zero-shot conversion. Our model outperforms existing state-of-the-art results in both subjective and objective evaluations. Furthermore, it facilitates cross-lingual voice conversions and enhances the quality of synthesized 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。
