Paper Info
Title
An Improved StarGAN for Emotional Voice Conversion - Enhancing Voice Quality and Data Augmentation.
Abstract
Emotional Voice Conversion (EVC) aims to convert the emotional style of a source speech signal to a target style while preserving its content and speaker identity information. Previous emotional conversion studies do not disentangle emotional information from emotion-independent information that should be preserved, thus transforming it all in a monolithic manner and generating audio of low quality, with linguistic distortions. To address this distortion problem, we propose a novel StarGAN framework along with a two-stage training process that separates emotional features from those independent of emotion by using an autoencoder with two encoders as the generator of the Generative Adversarial Network (GAN). The proposed model achieves favourable results in both the objective evaluation and the subjective evaluation in terms of distortion, which reveals that the proposed model can effectively reduce distortion. Furthermore, in data augmentation experiments for end-to-end speech emotion recognition, the proposed StarGAN model achieves an increase of 2% in Micro-F1 and 5% in Macro-F1 compared to the baseline StarGAN model, which indicates that the proposed model is more valuable for data augmentation.
Year
DOI
Venue
2021
10.21437/Interspeech.2021-1253
Interspeech
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Xiangheng He101.01
Junjie Chen26817.18
Georgios Rizos361.43
Björn Schuller46749463.50