publications

- Fully Automated Non-Native Speech Recognition Using Confusion-Based Acoustic Model Integration. Ghazi Bouselmi, Dominique Fohr, Irina Illina et Jean-Paul Haton. Interspeech'2005 - Eurospeech — 9th European Conference on Speech Communication and Technology. Lisbonne, Portugal, Septembre 2005.

- Fully Automated Non-Native Speech Recognition Using Confusion-Based Acoustic Model Integration And Graphemic Constraints. Ghazi Bouselmi, Dominique Fohr, Irina Illina et Jean-Paul Haton. IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2006. Toulouse, France, Mai 2006.

- Towards Speaker and Environmental Robustness in ASR: The HIWIRE Project. A. Potamianos, Ghazi Bouselmi, D. Dimitriadis, D. Fohr, R. Gemello, I. Illina, F. Mana, P. Maragos, M. Matassoni, V. Pitsikalis, J. Ramirez, E. Sanchez-Soto, J. Segura et P. Svaizer. IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2006. Toulouse, France, Mai 2006.

- Reconnaissance de parole non native fondée sur l'utilisation de confusion phonétique et de contraintes graphèmiques. Ghazi Bouselmi, Dominique Fohr, Irina Illina et Jean-Paul Haton. XXVIes Journées d'Etude sur la Parole - JEP'06. Saint-Malo, France, Juin 2006.

- Multilingual Non-Native Speech Recognition using Phonetic Confusion-Based Acoustic Model Modification and Graphemic Constraints. Ghazi Bouselmi, Dominique Fohr, Irina Illina et Jean-Paul Haton. The Ninth International Conference on Spoken Language Processing - ICSLP 2006. Pittsburgh, PA/USA, Septembre 2006.

- Discriminative Phoneme Sequences Extraction for Non-Native Speaker's Origin Classification. Ghazi Bouselmi, Dominique Fohr, Irina Illina et Jean-Paul Haton. International Symposium on Signal Processing and its Applications - ISSPA 2007. Sharjah, Emirats Arabe Unis (UAE), Février 2007.

- Détection de la langue maternelle de locuteurs non natifs fondée sur l'extraction de séquences discriminantes de phonèmes. Ghazi Bouselmi, Dominique Fohr, Irina Illina et Jean-Paul Haton. Traitement et Analyse de l'Information : Méthodes et Applications - TAIMA'07. Hammamet, Tunisie, Mai 2007.

- Combined Acoustic and Pronunciation Modelling for Non-Native Speech Recognition. Ghazi Bouselmi, Dominique Fohr et Irina Illina. Interspeech'2007/Eurospeech. Anvers, Belgique, Août 2007.

- Dynamic Gaussian Selection Technique For Speeding up HMM-Based Continuous Speech Recognition. Jun Cai, Ghazi Bouselmi, Dominique Fohr et Yves Laprie. IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2008. Toulouse, France, Mai 2006.

- Efficient Likelihood Evaluation and Dynamic Gaussian Selection for HMM-base Speech Recognition. Jun cai, Ghazi Bouselmi, Yves Laprie et Jean-Paul Haton. Computer Speech and Language - CSL. 2008.

- Multi-Accent and Accent-Independent Non-Native Speech Recognition. Ghazi Bouselmi, Dominique Fohr et Irina Illina. Interspeech'2008/Eurospeech. Brisbane, Australie, Septembre, 2008.

- Extended Partial Distance Elimination and Dynamic Gaussian Selection for Fast Likelihood Computation. Ghazi Bouselmi et Jun Cai . Interspeech'2008/Eurospeech. Brisbane, Australie, Septembre, 2008.

- Rapport de these: soutenue publiquement le 12 Novembre 2008.