MARY TTS HMM-based voices for the Blizzard Challenge 2012

Marcela Charfuelan Oliva

In: Proceedings of Blizzard Challenge 2012. SynSIG Blizzard Challenge September 14 Portland Oregon United States 2012.


This paper describes the first participation of MARY TTS HMM-based voices in a Blizzard challenge. An architecture for synthesis of expressive speech based on the MARY TTS system and sentiment analysis of text is proposed. The creation of several HMM-based voices in different styles using audiobook data is described. Preliminary results on perception of different voice styles and the appropriateness of a given style for a given sentence are presented. The latest developments in the open source MARY TTS 5.0 are briefly described.


dfki_blizzard2012.pdf (pdf, 230 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence