Sébastien Le Maguer - Research fellow

• Co-chair of SynSIG with Prof. Junichi Yamagishi (2017 - 2021)
• Co-organizer of SSW10, SSW11, DiSS 2021, HRI RoboIdentity 2022
• Help to the organization of the Blizzard challenge (2017 - )
• SimPhon.Net network (2017 - 2021)

• Member of ISCA (2009 - )

• Title : Experimental evaluation of statistical speech synthesis system, HTS, for French
• Supervisors : Olivier Boëffard, Nelly Barbot
• Defended the 2nd of July 2013
• Prix de l’innovation du Trégor

The work presented in this thesis is about TTS speech synthesis and, more particularly, about statistical speech synthesis for French. We present an analysis on the impact of the linguistic contextual factors on the synthesis achieved by the HTS statistical speech synthesis system. To conduct the experiments, two objective evaluation protocols are proposed. The first one uses Gaussian mixture models (GMM) to represent the acoustical space produced by HTS according to a contextual feature set. By using a constant reference set of natural speech stimuli, GMM can be compared between themselves and consequently acoustic spaces generated by HTS. The second objective evaluation that we propose is based on pairwise distances between natural speech and synthetic speech generated by HTS. Results obtained by both protocols, and confirmed by subjective evaluations, show that using a large set of contextual factors does not necessarily improve the modeling and could be counter-productive on the speech quality.

Keywords : Computer science, Speech processing, Text-to-Speech synthesis, HTS

PhD document (in french)