CycleTransGAN-EVC: A CycleGAN-based Emotional Voice Conversion Model with Transformer
Sound
2021-12-01 v1 Machine Learning
Audio and Speech Processing
Abstract
In this study, we explore the transformer's ability to capture intra-relations among frames by augmenting the receptive field of models. Concretely, we propose a CycleGAN-based model with the transformer and investigate its ability in the emotional voice conversion task. In the training procedure, we adopt curriculum learning to gradually increase the frame length so that the model can see from the short segment till the entire speech. The proposed method was evaluated on the Japanese emotional speech dataset and compared to several baselines (ACVAE, CycleGAN) with objective and subjective evaluations. The results show that our proposed model is able to convert emotion with higher strength and quality.
Keywords
Cite
@article{arxiv.2111.15159,
title = {CycleTransGAN-EVC: A CycleGAN-based Emotional Voice Conversion Model with Transformer},
author = {Changzeng Fu and Chaoran Liu and Carlos Toshinori Ishi and Hiroshi Ishiguro},
journal= {arXiv preprint arXiv:2111.15159},
year = {2021}
}