用于语音转换的节奏建模
Rhythm Modeling for Voice Conversion
AI总结：
本文提出无监督节奏转换方法 Urhythmic，通过自监督表示分段并建模时长分布、时间拉伸语音以匹配目标节奏，在音质和韵律上优于现有无监督方法。
摘要：
语音转换旨在将源语音转换为不同的目标声音。然而，典型的语音转换系统没有考虑节奏，而节奏是感知说话人身份的重要因素。为弥补这一差距，我们提出了 Urhythmic——一种无需并行数据或文本转写的无监督节奏转换方法。利用自监督表示，我们首先将源音频划分为近似响音、阻音和静音的片段。随后，我们通过估计语速或每种片段类型的时长分布来对节奏建模。最后，我们通过对语音片段进行时间拉伸来匹配目标语速或节奏。实验表明，Urhythmic 在音质和韵律方面优于现有的无监督方法。代码与检查点：https://github.com/bshall/urhythmic。音频演示页面：https://ubisoft-laforge.github.io/speech/urhythmic。
英文摘要：
Voice conversion aims to transform source speech into a different target voice. However, typical voice conversion systems do not account for rhythm, which is an important factor in the perception of speaker identity. To bridge this gap, we introduce Urhythmic-an unsupervised method for rhythm conversion that does not require parallel data or text transcriptions. Using self-supervised representations, we first divide source audio into segments approximating sonorants, obstruents, and silences. Then we model rhythm by estimating speaking rate or the duration distribution of each segment type. Finally, we match the target speaking rate or rhythm by time-stretching the speech segments. Experiments show that Urhythmic outperforms existing unsupervised methods in terms of quality and prosody. Code and checkpoints: https://github.com/bshall/urhythmic. Audio demo page: https://ubisoft-laforge.github.io/speech/urhythmic.
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。
