arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11004eess.AScs.CLcs.SD
收藏

NAUTILUS:一个多功能语音克隆系统

NAUTILUS: a Versatile Voice Cloning System

National Institute of Informatics(国立信息学研究所);SOKENDAI (The Graduate University for Advanced Studies)(综合研究大学院大学);Centre of Speech Technology Research, University of Edinburgh(爱丁堡大学语音技术研究中心)

Hieu-Thi Luong, Junichi Yamagishi

摘要:

我们介绍了一种新的语音合成系统,称为NAUTILUS,它可以生成语音与目标语音无论是从文本输入或参考话语的任意源扬声器。通过使用多说话人语音语料库训练所有必要的编码器和解码器在初始训练阶段,我们的系统可以克隆看不见的声音使用未转录的语音的目标说话人的反向传播算法的基础上。此外,根据目标说话者的数据环境,可以调整克隆策略以利用附加数据并修改文本到语音(TTS)和/或语音转换(VC)系统的行为以适应该情况。我们使用深度卷积层对编码器、解码器和WaveNet声码器进行建模,测试了所提出的框架的性能。评估表明,它实现了与国家的最先进的TTS和VC系统的质量时,克隆只有五分钟的未转录的语音。此外,它表明,该框架具有较高的说话人一致性,这将是有用的许多应用程序之间的TTS和VC切换的能力。

英文摘要:

We introduce a novel speech synthesis system, called NAUTILUS, that can generate speech with a target voice either from a text input or a reference utterance of an arbitrary source speaker. By using a multi-speaker speech corpus to train all requisite encoders and decoders in the initial training stage, our system can clone unseen voices using untranscribed speech of target speakers on the basis of the backpropagation algorithm. Moreover, depending on the data circumstance of the target speaker, the cloning strategy can be adjusted to take advantage of additional data and modify the behaviors of text-to-speech (TTS) and/or voice conversion (VC) systems to accommodate the situation. We test the performance of the proposed framework by using deep convolution layers to model the encoders, decoders and WaveNet vocoder. Evaluations show that it achieves comparable quality with state-of-the-art TTS and VC systems when cloning with just five minutes of untranscribed speech. Moreover, it is demonstrated that the proposed framework has the ability to switch between TTS and VC with high speaker consistency, which will be useful for many applications.

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。

↑