Sébastien Le Maguer
Overview
I am currently a postdoctoral researcher in the department of Digital Humanities of the University of Helsinki.
My research is centred around a fundamental question: what is a good synthetic speech? While my research was initially in computer science, addressing this question have led me to explore a more cross-disciplinary approach. Nowadays, my research is at the crossroad of (obviously) speech science and speech technology, but I also explore other fields such as HRI/HCI, auditory modelling and lately political science, ethics and (hopefully soon) sound-design.
In the past, I was a postdoctoral researcher and researcher fellow in the SIGMEDIA at the Trinity College Dublin (TCD) in the ADAPT Centre where I worked on speech synthesis evaluation. 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.
Activities
- 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)
Membership
- Member of ISCA (2009 - )
Research career & Activities
Current position
| Year | Description | Lab | Place |
|---|---|---|---|
| 01/24 | Post-Doctoral Researcher | Digital Humanities - University of Helsinki | Helsinki - Finland |
Past research experience
| Year | Description | team/group | Place |
|---|---|---|---|
| 10/18 - 12/23 | Post-Doctoral Researcher - Research Fellow | ADAPT Centre - Trinity College Dublin (IRC Grant, ADAPT2) | Dublin - Ireland |
| 10/14 - 09/18 | Post-Doctoral Researcher | MSP group - Saarland University | Saarbrücken - Germany |
| 02/14 - 09/14 | Post-Doctoral Researcher | LINKMEDIA - INRIA | Rennes - France |
| 09/13 - 12/13 | Post-Doctoral Researcher | CORDIAL - IRISA | Lannion - France |
| 09/11 - 08/13 | Research Engineer | CORDIAL - IRISA | Lannion - France |
| 10/08 - 07/13 | PhD | CORDIAL - IRISA | Lannion - France |
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
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 |
Public Engagement
- Natural Language Processing group Belarus Podcast (2016) - General Talk about speech synthesis - Part 1, Part2
- ADAPT Radio (2019) - Overview of my research
- Collaborator of CSDisseminate (2021)