O
Olivier Deroo
Researcher at Faculté polytechnique de Mons
Publications - 17
Citations - 836
Olivier Deroo is an academic researcher from Faculté polytechnique de Mons. The author has contributed to research in topics: Hidden Markov model & Speech synthesis. The author has an hindex of 10, co-authored 17 publications receiving 731 citations.
Papers
More filters
Journal ArticleDOI
Automatic speech recognition and speech variability: A review
Mohamed Faouzi BenZeghiba,R. De Mori,Olivier Deroo,Stéphane Dupont,T. Erbes,D. Jouvet,Luciano Fissore,Pietro Laface,Alfred Mertins,Christophe Ris,Richard Rose,Vivek Tyagi,Christian Wellekens +12 more
TL;DR: Current advances related to automatic speech recognition (ASR) and spoken language systems and deficiencies in dealing with variation naturally present in speech are outlined.
Journal ArticleDOI
Phonetic alignment: speech synthesis-based vs. viterbi-based
TL;DR: A method for the automatic creation of large phonetically labeled speech databases is deduced, based on using the synthetic speech segmentation tool to bootstrap the training process of either a HMM or a hybrid HMM/ANN system.
Proceedings ArticleDOI
Hybrid HMM/ANN systems for training independent tasks: experiments on Phonebook and related improvements
TL;DR: This paper evaluates multi-Gaussian HMM systems and hybrid HMM/ANN systems in the framework of task independent training for small size (75 words) and medium size (600 words) vocabularies and it is shown that the CMU lexicon leads to significantly better performance.
Proceedings Article
Capturing the intangible an introduction to the i-Treasures project
Kosmas Dimitropoulos,Sotiris Manitsaris,Filareti Tsalakanidou,Spiros Nikolopoulos,Bruce Denby,Samer Al Kork,Lise Crevier-Buchman,Claire Pillot-Loiseau,Martine Adda-Decker,Stéphane Dupont,Joëlle Tilmanne,Michela Ott,Marilena Alivizatou,Erdal Yilmaz,Leontios J. Hadjileontiadis,Vasileios Charisis,Olivier Deroo,Athanasios Manitsaris,Ioannis Kompatsiaris,Nikos Grammalidis +19 more
TL;DR: The i-Treasures project as mentioned in this paper aims at developing an open and extendable platform to provide access to ICH resources, enable knowledge exchange and contribute to the transmission of rare know-how.
Proceedings Article
Phonetic alignment: speech synthesis based vs. hybrid HMM/ANN.
TL;DR: A method is deduced for the automatic constitution of phonetically labeled speech databases based on using the synthetic speech segmentation tool to bootstrap the training process of the hybrid HMM/ANN system.