Primary goal of an emotional voice conversion (EVC) system is to convert the emotion of a given speech signal from one style to another style without modifying the linguistic content of the signal. Most of the state-of-the-art approaches convert emotions for seen speaker-emotion combinations only. In this paper, we tackle the problem of converting the emotion of speakers whose only neutral data are present during the time of training and testing (i.e., unseen speaker-emotion combinations). To this end, we extend a recently proposed StartGANv2-VC architecture by utilizing dual encoders for learning the speaker and emotion style embeddings separately along with dual domain source classifiers. For achieving the conversion to unseen speaker-emotion combinations, we propose a Virtual Domain Pairing (VDP) training strategy, which virtually incorporates the speaker-emotion pairs that are not present in the real data without compromising the min-max game of a discriminator and generator in adversarial training. We evaluate the proposed method using a Hindi emotional database.

翻译：情感声音转换（EVC）系统的核心目标是将给定语音信号的情感从一种风格转换为另一种风格，同时保持信号的 linguistic 内容不变。现有最先进的方法大多仅针对可见的说话人-情绪组合进行转换。本文致力于解决在训练和测试阶段仅存在中性数据（即未见说话人-情绪组合的情况下）的说话人情感转换问题。为此，我们扩展了近期提出的 StartGANv2-VC 架构，通过采用双编码器分别学习说话人和情感风格嵌入，并联合使用双域源分类器。为实现对未见说话人-情绪组合的转换，我们提出了一种虚拟域配对（VDP）训练策略，该策略在不破坏对抗训练中判别器与生成器之间最小-最大博弈的前提下，虚拟地整合了实际数据中不存在的说话人-情绪配对。我们使用印地语情感数据库对所提出的方法进行了评估。