EmoSpeech：引导 FastSpeech2 走向情感文本到语音
EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech
AI总结：
本文以FastSpeech2为基础提出EmoSpeech模型，通过引入处理情感不均匀分布的条件机制等修改，有效提升了合成语音的MOS分数和情感识别准确率及表现力。
摘要：
最先进的语音合成模型试图尽可能接近人类声音。因此，情感建模是文本到语音（TTS）研究的重要组成部分。在我们的工作中，我们选择 FastSpeech2 作为起点，并提出了一系列用于合成情感语音的修改。根据自动和人工评估，我们的模型 EmoSpeech 在生成语音的 MOS 分数和情感识别准确率方面均超越了现有模型。我们为构成 EmoSpeech 的 FastSpeech2 架构的每一项扩展提供了详细的消融研究。文本中情感的不均匀分布对于更好的合成语音和语调感知至关重要。我们的模型包含一个条件机制，通过允许情感以不同的强度水平贡献给每个音素，有效地处理了这一问题。人工评估表明，所提出的修改生成了具有更高 MOS 和情感表现力的音频。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
