SS-5: Dealing with Intrinsic Speech Variabilities in ASR |
| Session Type: Special Lecture |
| Time: Wednesday, May 17, 14:00 - 16:00 |
| Location: Guillaumet 1 & 2 |
| Chair: Stéphane Dupont, Multitel |
| SS-5.1: AUTOMATIC SPEECH RECOGNITION AND INTRINSIC SPEECH VARIATION |
| Mohamed Benzeguiba, Eurecom Institute, France; Renato De Mori, Université d'Avignon, France; Olivier Deroo, Acapela Group, Belgium; Stéphane Dupont, Multitel ASBL, Belgium; Teodora Erbes, Eurecom Institute, France; Denis Jouvet, France Télécom, France; Luciano Fissore, Loquendo, Italy; Pietro Laface, Politecnico di Torino, Italy; Alfred Mertins, Carl von Ossietzky Universitat Oldenburg, Germany; Christophe Ris, Multitel, Belgium; Richard Rose, McGill University, Canada; Vivek Tyagi, Christian Wellekens, Eurecom Institute, France |
| SS-5.2: FREQUENCY-WARPING INVARIANT FEATURES FOR AUTOMATIC SPEECH RECOGNITION |
| Alfred Mertins, Jan Rademacher, University of Oldenburg, Germany |
| SS-5.3: CHARACTERIZING FEATURE VARIABILITY IN AUTOMATIC SPEECH RECOGNITION SYSTEMS |
| Loïc Barrault, Driss Matrouf, Renato De Mori, University of Avignon, France; Roberto Gemello, Franco Mana, Loquendo, Italy |
| SS-5.4: ADAPTATION OF HYBRID ANN/HMM USING WEIGHTS INTERPOLATION |
| Stefano Scanzio, Pietro Laface, Politecnico di Torino, Italy; Roberto Gemello, Franco Mana, Loquendo, Italy |
| SS-5.5: USING MULTILINGUAL UNITS FOR IMPROVED MODELING OF PRONUNCIATION VARIANTS |
| Katarina Bartkova, Denis Jouvet, France Télécom R&D Division, France |
| SS-5.6: FEPSTRUM AND CARRIER SIGNAL DECOMPOSITION OF SPEECH SIGNALS THROUGH HOMOMORPHIC FILTERING |
| Vivek Tyagi, Christian Wellekens, Institut Eurecom, France |
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012