@inproceedings{lorenzo2017investigating,
  title={Investigating different representations for modeling multiple emotions in {DNN}-based speech synthesis},
  author={Lorenzo-Trueba, Jaime and Henter, Gustav Eje and Takaki, Shinji and Yamagishi, Junichi and Morino, Yosuke and Ochiai, Yuta},
  booktitle={Proc. International Workshop on Affective Social Multimedia Computing (ASMMC)},
  abstract={This paper investigates simultaneous modeling of multiple emotions in DNN-based expressive speech synthesis, and how to represent the emotional labels, such as emotional class and strength, for this task. Our goal is to answer two questions: First, what is the best way to annotate speech data with multiple emotions -- should we use the labels that the speaker intended to express, or labels based on listener perception of the resulting speech signals? Second, how should the emotional information be represented as labels for supervised DNN training, e.g., should emotional class and emotional strength be factorized into separate inputs or not? We evaluate on a large-scale corpus of emotional speech from a professional actress, additionally annotated with perceived emotional labels from crowdsourced listeners. By comparing DNN-based speech synthesizers that utilize different emotional representations, we assess the impact of these representations and design decisions on human emotion recognition rates and perceived emotional strength.},
  keywords={emotional speech synthesis, deep neural network, recurrent neural networks},
  address={Stockholm, Sweden},
  month={Aug.},
  volume={3},
  year={2017}
}