English

Adjusting Pleasure-Arousal-Dominance for Continuous Emotional Text-to-speech Synthesizer

Audio and Speech Processing 2022-11-28 v1 Machine Learning Sound

Abstract

Emotion is not limited to discrete categories of happy, sad, angry, fear, disgust, surprise, and so on. Instead, each emotion category is projected into a set of nearly independent dimensions, named pleasure (or valence), arousal, and dominance, known as PAD. The value of each dimension varies from -1 to 1, such that the neutral emotion is in the center with all-zero values. Training an emotional continuous text-to-speech (TTS) synthesizer on the independent dimensions provides the possibility of emotional speech synthesis with unlimited emotion categories. Our end-to-end neural speech synthesizer is based on the well-known Tacotron. Empirically, we have found the optimum network architecture for injecting the 3D PADs. Moreover, the PAD values are adjusted for the speech synthesis purpose.

Keywords

Cite

@article{arxiv.1906.05507,
  title  = {Adjusting Pleasure-Arousal-Dominance for Continuous Emotional Text-to-speech Synthesizer},
  author = {Azam Rabiee and Tae-Ho Kim and Soo-Young Lee},
  journal= {arXiv preprint arXiv:1906.05507},
  year   = {2022}
}

Comments

Interspeech2019, Show and Tell demonstration https://www.youtube.com/watch?v=MAOk_ZxuA0I&feature=youtu.be