arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.07537eess.AScs.LGcs.SD
收藏

走向降级-鲁棒的语音转换

Toward Degradation-Robust Voice Conversion

National Taiwan University(台湾大学)

Chien-yu Huang, Kai-Wei Chang, Hung-yi Lee

摘要:

任何到任何语音转换技术将话语的音色转换为任何扬声器,即使在训练期间看不见。虽然已经有几种最先进的任意语音转换模型,但它们都是基于干净的话语来成功转换的。然而,在现实世界的场景中,很难收集说话者的干净话语,并且它们通常被噪声或混响降级。因此,非常需要了解这些退化如何影响语音转换并建立退化鲁棒模型。我们在本文中报告的第一个全面的研究退化鲁棒性的任何到任何语音转换。我们发现,性能的国家的最先进的模型,现在受到严重阻碍,退化的话语。为此,我们提出了语音增强级联和去噪训练,以提高鲁棒性。除了常见的退化之外,我们还考虑了对抗性噪声,这些噪声会显著改变模型输出,但人类无法感知。实验结果表明,与现有语音增强模型的级联和对语音转换模型的去噪训练都能提高鲁棒性,但各有优缺点。

英文摘要:

Any-to-any voice conversion technologies convert the vocal timbre of an utterance to any speaker even unseen during training. Although there have been several state-of-the-art any-to-any voice conversion models, they were all based on clean utterances to convert successfully. However, in real-world scenarios, it is difficult to collect clean utterances of a speaker, and they are usually degraded by noises or reverberations. It thus becomes highly desired to understand how these degradations affect voice conversion and build a degradation-robust model. We report in this paper the first comprehensive study on the degradation robustness of any-to-any voice conversion. We show that the performance of state-of-the-art models nowadays was severely hampered given degraded utterances. To this end, we then propose speech enhancement concatenation and denoising training to improve the robustness. In addition to common degradations, we also consider adversarial noises, which alter the model output significantly yet are human-imperceptible. It was shown that both concatenations with off-the-shelf speech enhancement models and denoising training on voice conversion models could improve the robustness, while each of them had pros and cons.

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。

↑