@InProceedings{lorenzotrueba-EtAl:2016:COLING,
  author    = {Lorenzo-Trueba, Jaime  and  Barra-Chicote, Roberto  and  Gallardo-Antolin, Ascension  and  Yamagishi, Junichi  and  Montero, Juan M},
  title     = {Continuous Expressive Speaking Styles Synthesis based on CVSM and MR-HMM},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {369--376},
  abstract  = {This paper introduces a continuous system capable of automatically producing
	the most adequate speaking style to synthesize a desired target text. This is
	done thanks to a joint modeling of the acoustic and lexical parameters of the
	speaker models by adapting the CVSM projection of the training texts using
	MR-HMM techniques. As such, we consider that as long as sufficient variety in
	the training data is available, we should be able to model a continuous lexical
	space into a continuous acoustic space. The proposed continuous automatic text
	to speech system was evaluated by means of a perceptual evaluation in order to
	compare them with traditional approaches to the task. The system proved to be
	capable of conveying the correct expressiveness (average adequacy of 3.6) with
	an expressive strength comparable to oracle traditional expressive speech
	synthesis (average of 3.6) although with a drop in speech quality mainly due to
	the semi-continuous nature of the data (average quality of 2.9). This means
	that the proposed system is capable of improving traditional neutral systems
	without requiring any additional user interaction.
	Author{2}{Affiliation}},
  url       = {http://aclweb.org/anthology/C16-1036}
}