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.

中文翻译：

---

用于情感语音转换的改进 StarGAN：提高语音质量和数据增强

情感语音转换 (EVC) 旨在将源语音信号的情感风格转换为目标风格，同时保留其内容和说话者身份信息。以前的情绪转换研究并没有将情绪信息与应保留的情绪独立信息分开，从而以整体方式将其全部转换并生成低质量的音频，并带有语言失真。为了解决这个失真问题，我们提出了一个新的 StarGAN 框架以及一个两阶段的训练过程，通过使用带有两个编码器的自动编码器作为生成对抗网络 (GAN) 的生成器，将情感特征与独立于情感的特征分开。所提出的模型在失真方面在客观评价和主观评价中均取得了良好的结果，这表明所提出的模型可以有效地减少失真。此外，在端到端语音情感识别的数据增强实验中，与基线 StarGAN 模型相比，所提出的 StarGAN 模型在 Micro-F1 中实现了 2% 的增长，在 Macro-F1 中实现了 5% 的增长，这表明所提出的模型对数据增强更有价值。