arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.09708cs.SDcs.CLeess.AS
收藏

使用多模态学习改进Few-Shot语音克隆

Improve few-shot voice cloning using multi-modal learning

NetEase Games AI Lab(网易游戏AI实验室)

Haitong Zhang, Yue Lin

摘要:

近年来,Few-Shot语音克隆技术取得了显著的进步。然而,大多数用于Few-Shot语音克隆的模型是单模态的,并且多模态的Few-Shot语音克隆尚未得到充分研究。在本文中,我们提出使用多模态学习来提高Few-Shot语音克隆的性能。受最近无监督语音表示工作的启发,建议的多模态系统是通过扩展Tacotron 2与无监督语音表示模块来构建的。我们评估我们提出的系统在两个Few-Shot语音克隆的情况下,即Few-Shot文本到语音(TTS)和语音转换(VC)。实验结果表明,所提出的多模态学习可以显着提高Few-Shot的语音克隆性能比他们的对应单模态系统。

英文摘要:

Recently, few-shot voice cloning has achieved a significant improvement. However, most models for few-shot voice cloning are single-modal, and multi-modal few-shot voice cloning has been understudied. In this paper, we propose to use multi-modal learning to improve the few-shot voice cloning performance. Inspired by the recent works on unsupervised speech representation, the proposed multi-modal system is built by extending Tacotron2 with an unsupervised speech representation module. We evaluate our proposed system in two few-shot voice cloning scenarios, namely few-shot text-to-speech(TTS) and voice conversion(VC). Experimental results demonstrate that the proposed multi-modal learning can significantly improve the few-shot voice cloning performance over their counterpart single-modal systems.

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。

↑