DeepAI AI Chat
Log In Sign Up

Converting Anyone's Emotion: Towards Speaker-Independent Emotional Voice Conversion

by   Kun Zhou, et al.
National University of Singapore

Emotional voice conversion aims to convert the emotion of the 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 believe that emotions are expressed universally across speakers, therefore, the speaker-independent mapping between emotional states of speech is possible. In this paper, we propose to build 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.


page 1

page 2

page 3

page 4


Identity Conversion for Emotional Speakers: A Study for Disentanglement of Emotion Style and Speaker Identity

Expressive voice conversion performs identity conversion for emotional s...

Decoupling Speaker-Independent Emotions for Voice Conversion Via Source-Filter Networks

Emotional voice conversion (VC) aims to convert a neutral voice to an em...

Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset

Emotional voice conversion aims to transform emotional prosody in speech...

VAW-GAN for Disentanglement and Recomposition of Emotional Elements in Speech

Emotional voice conversion (EVC) aims to convert the emotion of speech f...

EmoCat: Language-agnostic Emotional Voice Conversion

Emotional voice conversion models adapt the emotion in speech without ch...

MASS: Multi-task Anthropomorphic Speech Synthesis Framework

Text-to-Speech (TTS) synthesis plays an important role in human-computer...