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

Azam Rabiee, Tae-Ho Kim, Soo-Young Lee


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.


Cite as: Rabiee, A., Kim, T., Lee, S. (2019) Adjusting Pleasure-Arousal-Dominance for Continuous Emotional Text-to-Speech Synthesizer. Proc. Interspeech 2019, 3693-3694.


@inproceedings{Rabiee2019,
  author={Azam Rabiee and Tae-Ho Kim and Soo-Young Lee},
  title={{Adjusting Pleasure-Arousal-Dominance for Continuous Emotional Text-to-Speech Synthesizer}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={3693--3694}
}