Sébastien Le Maguer

Post-doctoral research fellow

Table of Contents

1 Global information

I am currently a Research Fellow in the SIGMEDIA at the Trinity College Dublin (TCD) in the ADAPT Centre. I am currently funded by the GOIPD scheme from the Irish Research Council (IRC).

My research is centred around a fundamental question: what is natural speech? To conduct my research, I am currently focusing my work around two axes: speech synthesis evaluation/analysis and analyzing stuttering speech.

In the past, I was a postdoctoral researcher at Saarland University/DFKI (Germany) where I worked on integration and evaluation of the influence of information density features in speech synthesis; at INRIA/IRISA in Rennes (France) where I worked on information retrieval with an application on medical context. I did my PhD on parametric speech synthesis evaluation at IRISA/Université de Rennes 1.

1.1 Activites

1.2 Membership

  • Member of ISCA (2009 - )

2 Research career

2.1 Current position

Year Description team/group Place Supervisor
10/18 Post-doctoral research fellow ADAPT Centre - Trinity College Dublin Dublin - Ireland Prof. Naomi Harte

2.2 Past research experience

Year Description team/group Place Supervisor(s)
10/14 - 09/18 Post-Doc MSP group - Saarland University Saarbrücken - Germany Dr. Ingmar Steiner
02/14 - 09/14 Post-Doc LINKMEDIA - INRIA Rennes - France Dr. Vincent Claveau
09/13 - 12/13 Post-Doc CORDIAL - IRISA Lannion - France Dr. Damien Lolive / Dr. Nelly Barbot
09/11 - 08/13 Research Assistant CORDIAL - IRISA Lannion - France Prof. Olivier Boëffard / Dr. Nelly Barbot
10/08 - 07/13 PhD CORDIAL - IRISA Lannion - France Prof. Olivier Boëffard / Dr. Nelly Barbot

2.3 PhD

  • 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)

3 Education

Année Level Topic Place
2008 - 2013 Doctorate Degree Computer science Université de Rennes 1, France
2006 - 2008 Master of science Computer science - Complex systems and algorihms Université de Lille 1, France
2005 - 2006 Bachelor’s Degree Computer science - A.I and robotic U.B.O. (Brest), France
2003 - 2005 DUT Computer science - software design and engineering IUT de Lannion, France

4 Technical skills

  • Programming :
    • skilled : Perl, C, C++, Java, Python, Php, Shells, Matlab
    • fundamentals : Scheme/(E)Lisp
  • Systems : Linux, Windows
  • Foreign Language : English (Written and Spoken), German (basics), French (Native)

5 Publications

Author: Sébastien Le Maguer

Created: 2020-11-25 Wed 11:22

Emacs 27.1 (Org mode 9.4)