arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.09634eess.AScs.CLcs.LGcs.SD
收藏

基于变分自动编码器的跨域特征语音转换

Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders

Institute of Information Science, Academia Sinica(中央研究院信息科学研究所);National Taiwan University(台湾大学);Research Center for Information Technology Innovation, Academia Sinica(中央研究院信息科技创新研究中心)

Wen-Chin Huang, Hsin-Te Hwang, Yu-Huai Peng, Yu Tsao, Hsin-Min Wang

摘要:

非并行语音转换(VC)的一种有效方法是利用深度神经网络(DNN),特别是变分自动编码器(VAE),以无监督的方式对语音的潜在结构进行建模。以前的研究已经证实了VAE的有效性,使用直光谱VC。然而,VAE使用的其他类型的频谱特征,如梅尔倒谱系数(MCC),这是与人类的感知和已被广泛用于VC,没有得到适当的研究。代替使用一种特定类型的光谱特征,预期VAE可以受益于同时使用多种类型的光谱特征,从而提高VAE用于VC的能力。为此,我们提出了一种新的VAE框架(称为跨域VAE,CDVAE)的VC。具体地,所提出的框架通过显式地正则化多个目标来利用STRAIGHT谱和MCC两者,以便约束学习的编码器和解码器的行为。实验结果表明,提出的CD-VAE框架优于传统的VAE框架的主观测试。

英文摘要:

An effective approach to non-parallel voice conversion (VC) is to utilize deep neural networks (DNNs), specifically variational auto encoders (VAEs), to model the latent structure of speech in an unsupervised manner. A previous study has confirmed the ef- fectiveness of VAE using the STRAIGHT spectra for VC. How- ever, VAE using other types of spectral features such as mel- cepstral coefficients (MCCs), which are related to human per- ception and have been widely used in VC, have not been prop- erly investigated. Instead of using one specific type of spectral feature, it is expected that VAE may benefit from using multi- ple types of spectral features simultaneously, thereby improving the capability of VAE for VC. To this end, we propose a novel VAE framework (called cross-domain VAE, CDVAE) for VC. Specifically, the proposed framework utilizes both STRAIGHT spectra and MCCs by explicitly regularizing multiple objectives in order to constrain the behavior of the learned encoder and de- coder. Experimental results demonstrate that the proposed CD- VAE framework outperforms the conventional VAE framework in terms of subjective tests.

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。

↑