Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion

Autor:	Chen, Yun, Yang, Lingxiao, Chen, Qi, Lai, Jian-Huang, Xie, Xiaohua
Rok vydání:	2023
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Artificial Intelligence Computer Science - Sound
Druh dokumentu:	Working Paper
DOI:	10.21437/Interspeech.2023-39
Popis:	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. Comment: Accepted by INTERSPEECH 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2312.17508 Zobrazit plný text záznamu View this record from Arxiv