论文标题
向我阅读：一种情感意识的语音叙述应用
Read it to me: An emotionally aware Speech Narration Application
论文作者
论文摘要
在这项工作中，我们尝试在音频上进行情感风格转移。特别是，探索了各种情感对转移的梅尔根-VC架构。然后使用基于LSTM的情感分类器进行音频进行分类。我们发现，与“快乐”或“愤怒”相比，“悲伤”的音频具有很好的表现，因为人们也有类似的悲伤表达。
In this work we try to perform emotional style transfer on audios. In particular, MelGAN-VC architecture is explored for various emotion-pair transfers. The generated audio is then classified using an LSTM-based emotion classifier for audio. We find that "sad" audio is generated well as compared to "happy" or "anger" as people have similar expressions of sadness.
