converting anyone s emotion towards speaker independent emotional voice conversion

• DOI: 10.48550/arxiv.2005.07025
• Publication Date: 2020-10-25
• Authors: Berrak Sisman; Kun Zhou; Mingyang Zhang; Haizhou Li
• Keywords: FOS: Computer and information sciences; Sound (cs.SD); Computer Science - Computation and Language; Computer Science - Artificial Intelligence; 02 engineering and technology; Computer Science - Sound; Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS); FOS: Electrical engineering, electronic engineering, information engineering; 0202 electrical engineering, electronic engineering, information engineering; Computation and Language (cs.CL); Electrical Engineering and Systems Science - Audio and Speech Processing

Accepted by Interspeech 2020<br/>Emotional voice conversion aims to convert the emotion of speech from one state to another while preserving the linguistic content and speaker identity. The prior studies on emotional voice conversion are mostly carried out under the assumption that emotion is speaker-dependent. We consider that there is a common code between speakers for emotional expression in a spoken language, therefore, a speaker-independent mapping between emotional states is possible. In this paper, we propose a speaker-independent emotional voice conversion framework, that can convert anyone's emotion without the need for parallel data. We propose a VAW-GAN based encoder-decoder structure to learn the spectrum and prosody mapping. We perform prosody conversion by using continuous wavelet transform (CWT) to model the temporal dependencies. We also investigate the use of F0 as an additional input to the decoder to improve emotion conversion performance. Experiments show that the proposed speaker-independent framework achieves competitive results for both seen and unseen speakers.<br/>