Emotional Voice Conversion aims to manipulate a speech according to a given emotion while preserving non-emotion components. Existing approaches cannot well express fine-grained emotional attributes. In this paper, we propose an Attention-based Interactive diseNtangling Network (AINN) that leverages instance-wise emotional knowledge for voice conversion. We introduce a two-stage pipeline to effectively train our network: Stage I utilizes inter-speech contrastive learning to model fine-grained emotion and intra-speech disentanglement learning to better separate emotion and content. In Stage II, we propose to regularize the conversion with a multi-view consistency mechanism. This technique helps us transfer fine-grained emotion and maintain speech content. Extensive experiments show that our AINN outperforms state-of-the-arts in both objective and subjective metrics.
@article{arxiv.2312.17508,
title = {Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion},
author = {Yun Chen and Lingxiao Yang and Qi Chen and Jian-Huang Lai and Xiaohua Xie},
journal= {arXiv preprint arXiv:2312.17508},
year = {2024}
}