Thomas Pellegrini

From L²F

Thomas Pellegrini

Update September 2013: I moved to Université de Toulouse III, my new webpage: http://www.irit.fr/~Thomas.Pellegrini

Thomas Pellegrini graduated in Physics at the Ecole Supérieure de Physique et de Chimie Industrielles of Paris (ESPCI) in 2003. He received a Masters Degree in Acoustics, Signal Processing, Computer Science Applied to Music in 2003 at IRCAM, Paris VI University (ATIAM). He received a PhD in Computer Science in 2008 at LIMSI-CNRS from the Paris-Sud University, on Speech Recognition for Less-represented Languages. He has been a teaching assistant at Paris La Sorbonne during 2007-2008, teaching mainly object-oriented programming. Since september 2008, he is a post-doc at Spoken Language Systems Lab (L²F).

INESC ID Information

Publications

International Journals

2013

  • Thomas Pellegrini, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede, Maxine Eskenazi, ASR-based exercises for listening comprehension practice in European Portuguese, Computer Speech and Language, doi: http://dx.doi.org/10.1016/j.csl.2013.02.004, February 2013

2009

  • Thomas Pellegrini, Lori Lamel, Automatic word decompounding for ASR in a morphologically rich language: application to Amharic, IEEE Transactions on Audio, Speech, and Language Processing,, IEEE Signal Processing Society , vol. 17, n. 5, pages 863 - 873, July 2009

International Conferences

2015

2014

  • Annika Hamalainen, Hugo Meinedo, Michael Tjalve, Thomas Pellegrini, Isabel Trancoso, Miguel Sales Dias, Improving Speech Recognition through Automatic Selection of Age Group –Specific Acoustic Models, In 11th International Conference on Computational Processing of the Portuguese Language, PROPOR 2014, Springer, series Lecture Notes on Artificial Intelligence, doi: 10.1007/978-3-319-09761-9_2, São Carlos, SP, Brazil, October 2014

2013

2012

  • Isabel Trancoso, Thomas Pellegrini, André Freire Silva, Rui Correia, Nuno J. Mamede, Jorge Baptista, Learning Portuguese with Speech Technologies, In IBERSPEECH 2012, pages 411-414, Demo paper, Madrid, Spain, November 2012

2011

2010

  • José Lopes, Isabel Trancoso, Rui Correia, Thomas Pellegrini, Hugo Meinedo, Nuno J. Mamede, Maxine Eskenazi, Multimedia Learning Materials, In IEEE Spoken Language Technology Workshop, IEEE, Berkeley, USA, December 2010

2009

  • Isabel Trancoso, Thomas Pellegrini, José Portêlo, Hugo Meinedo, Miguel Bugalho, Alberto Abad, João Paulo da Silva Neto, Audio contributions to semantic video search, In 2009 IEEE International Conference on Multimedia and Expo (ICME 2009), IEEE, New York, USA, June 2009
  • Ebru Arisoy, Thomas Pellegrini, Murat Saraclar, Lori Lamel, Enhanced Morfessor Algorithm with Phonetic Features: application to Turkish, In SPECOM, June 2009

MSc theses

Finished

  • 3P - Portuguese Pronunciation Professor, Mariana Sofia Pimenta Lopes. Instituto Superior Técnico (2013-2014). Isabel Trancoso, advisor. Thomas Pellegrini, co-advisor.
  • Áudio Descrição de Filmes, Virgínia Maria Martins Barbosa. Instituto Superior Técnico, Universidade Técnica de Lisboa (2009-2011). Isabel Trancoso, advisor. Thomas Pellegrini, co-advisor.

Research Interests

Languages, Automatic Speech Recognition, Audio, Music and Sound in general.

Publications

Thesis