期刊
2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
卷 -, 期 -, 页码 7769-7773出版社
IEEE
DOI: 10.1109/icassp40776.2020.9054534
关键词
Emotional Voice Conversion; Variational Autoencoder; Disentangled Representation; Style Transfer
资金
- Seoul RBD Program [CY190019]
- Institute of Information & Communications Technology Planning & Evaluation(IITP) - Korea government (MSIT)
Due to the complexity of emotional features, there has been limited success in emotional voice conversion. One major challenge is that conversion between more than two kinds of emotions often accompanies distortion of voice signal. The factorized hierarchical variational autoencoder (FHVAE) [1] was previously shown to have an ability, called sequence-level regularization, to generate disentangled representations of both sequence-level (such as speaker identity) and segment-level features. This study exploits the FHVAE pipeline to produce disentangled representations of emotion, making it possible to greatly facilitate emotional voice conversion. We propose three versions of algorithms for improving the quality of disentangled representation and audio synthesis. We conducted three mean opinion score (MOS) surveys to assess the performance of our models in terms of 1) speaker's voice preservation, 2) emotion conversion, and 3) audio naturalness.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据