arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.08009eess.AScs.SD
收藏

使用规范化流的无文本非并行多对多语音转换

Text-free non-parallel many-to-many voice conversion using normalising flows

Amazon(亚马逊)

Thomas Merritt, Abdelhamid Ezzerg, Piotr Biliński, Magdalena Proszewska, Kamil Pokora, Roberto Barra-Chicote, Daniel Korzekwa

摘要:

非并行语音转换(VC)通常使用源语音的有损表示来实现。然而,确保只有说话者身份信息被丢弃,而来自源语音的所有其他信息被保留是一个很大的挑战。这在推理时我们不知道正在阅读的文本的情况下尤其具有挑战性,即,无文本VC.为了减轻这一点,我们研究信息保存VC方法。规范化流已经获得了文本到语音合成的关注,但是对于VC还没有充分探索。流利用可逆函数来学习数据的可能性,从而提供语音的无损编码。我们调查正常化流VC在文本条件和文本自由的情况下。此外,对于无文本VC,我们比较了预训练和联合学习的先验知识。基于流的VC评估显示无文本VC和有文本条件的VC之间没有退化,从而改善了现有技术。此外,联合训练的先验被发现对无文本VC质量产生负面影响。

英文摘要:

Non-parallel voice conversion (VC) is typically achieved using lossy representations of the source speech. However, ensuring only speaker identity information is dropped whilst all other information from the source speech is retained is a large challenge. This is particularly challenging in the scenario where at inference-time we have no knowledge of the text being read, i.e., text-free VC. To mitigate this, we investigate information-preserving VC approaches. Normalising flows have gained attention for text-to-speech synthesis, however have been under-explored for VC. Flows utilize invertible functions to learn the likelihood of the data, thus provide a lossless encoding of speech. We investigate normalising flows for VC in both text-conditioned and text-free scenarios. Furthermore, for text-free VC we compare pre-trained and jointly-learnt priors. Flow-based VC evaluations show no degradation between text-free and text-conditioned VC, resulting in improvements over the state-of-the-art. Also, joint-training of the prior is found to negatively impact text-free VC quality.

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。

↑