Publications of Frédéric Berthommier sorted by recency
| Test of several external posterior weighting functions for multiband Full Combination ASR, and , Idiap-RR-27-2000 |
|
| Reconnaissance robuste de la parole par segmentation signal/bruit en sous-bandes, , , and , in: Neurosciences et Sciences de l'Ingenieur'98 - Munster, CNRS, 1998 |
|
| Reconnaissance multi-bandes de la parole bruitée par couplage entre les niveaux primitifs et d'identification, , , and , in: Journees Etude Parole - Martigny, 1998 |
|
| Interfacing of CASA and partial recognition based on a multistream technique, , , and , in: ICSLP'98, Sidney, 1998 |
|
| Interfacing of CASA and Multistream recognition, , , and , in: TSD'98-Text, Speech and Dialog International Workshop, BRNO-Czech Republic, 1998 |
|
| Blind separation of delayed and superimposed acoustic sources : learning algorithms an experimental study, , , , and , in: Proc. IEEE Int. Conference on Speech Processing (ICSP), IEEE, 1999 |
| A new SNR-feature mapping for robust multistream speech recognition, and , in: Proc. Int. Congress on Phonetic Sciences (ICPhS), 1999 |
| A measure of speech and pitch reliability from voicing, and , in: Proc. Int. Joint Conf. on Artificial Intelligence (IJCAI), Scandinavian AI Society, 1999 |
| A CASA-labelling model using the localisation cue for robust cocktail-party speech recognition, , and , in: Proc.\ European Conf.\ on Speech Communication and Technology (EUROSPEECH), 1999 |
| A CASA front-end using the localisation cue for segregation and then cocktail-party speech recognition, , , and , in: Proc. IEEE Int. Conference on Speech Processing (ICSP), IEEE, 1999 |
| Test of several external posterior weighting functions for multiband Full Combination ASR, and , in: Int. Conf. on Spoken Language Processing (ICSLP), 2000 |
| Reconnaissance de la parole dans le bruit après renforcement fondé sur l'harmonicité, and , in: Proceedings of JEP'2000, no IDIAP RR, see RESPITE www, 2000 |
| Multichannel signal separation for cocktail party speech recognition: a dynamic recurrent network, , , and , in: Int. Conf. on Spoken Language Processing (ICSLP), no IDIAP RR, see RESPITE www, 2000 |
| Blind acoustic source separation for cocktail party speech recognition, , , and , in: ICONIP, 7th IEEE Int. Conf. on Neural Information Processing, 2000 |
| A front-end using the harmonicity cue for speech enhancement in loud noise, , and , in: Int. Conf. on Spoken Language Processing (ICSLP), 2000 |