State-of-the-art speech synthesis models try to get as close as possible to the human voice. Hence, modelling emotions is an essential part of Text-To-Speech (TTS) research. In our work, we selected FastSpeech2 as the starting point and proposed a series of modifications for synthesizing emotional speech. According to automatic and human evaluation, our model, EmoSpeech, surpasses existing models regarding both MOS score and emotion recognition accuracy in generated speech. We provided a detailed ablation study for every extension to FastSpeech2 architecture that forms EmoSpeech. The uneven distribution of emotions in the text is crucial for better, synthesized speech and intonation perception. Our model includes a conditioning mechanism that effectively handles this issue by allowing emotions to contribute to each phone with varying intensity levels. The human assessment indicates that proposed modifications generate audio with higher MOS and emotional expressiveness.

翻译：最先进的语音合成模型力求尽可能接近人声。因此，情感建模是文本到语音（TTS）研究的重要组成部分。在本工作中，我们以FastSpeech2为起点，提出了一系列用于合成情感语音的改进方案。根据自动评估和人工评估，我们的模型EmoSpeech在生成语音的MOS得分和情感识别准确率方面均超越了现有模型。我们对构成EmoSpeech的FastSpeech2架构的每项扩展进行了详细消融研究。文本中情感的非均匀分布对于提升合成语音质量及语调感知至关重要。我们的模型包含一种条件机制，通过允许情感以不同强度水平作用于每个音素，有效地解决了这一问题。人工评估表明，所提出的改进方案生成的音频具有更高的MOS值和情感表现力。