Spoken language processing: from perceptron to deep learning
Date: 14 April
Time: 12:00 pm
Location: Room Garda, Polo Scientifico e Tecnologico “Fabio Ferrari”, Building Povo 1 - Povo (Trento)
Prof. Renato De Mori, Emeritus Professor at McGill University (Canada) and at the University of Avignon (France)
Recent advances in neural models for automatic speech recognition and spoken language understanding are discussed in an evolutional perspective. The first attempts based on perceptron and finite state automata, the early artificial intelligence dreams, the raise of interest with multi-layer perceptron obscured by the first impressive successes of statistical models and the resurgence of interest in neural models are briefly reviewed. Some recent results on automatic speech recognition, machine translation, spoken language understanding obtained with latent, not only neural, features are presented with focus on the recently started CHIST-ERA EU/Canadian project.
About the Speaker
Renato De Mori is emeritus professor at Mc Gill University (Canada) and at the University of Avignon (France). He has been full professor in Italy (University of Turin), Canada and France. He is a Fellow of the Computer Society and has been distinguished lecturer of the Signal Processing Society of the Institute of Electrical and Electronic Engineers (IEEE). He has been scientific leader of projects in Canada (The Institute for Robotics and Intelligent Systems, a Canadian Network of Centers of Excellence) and in Europe (Language Understanding for telephone Applications LUNA http://www.ist-luna.eu).
He has been overview Editor of the IEEE Transactions of the Signal Processing Society( (2009-2012), Chief Editor of Speech Communication (2003-2005) (member of the editorial board since 1982), associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence (1998-1992) and the IEEE Transactions on Audio, Speech and Language Processing (2009-2014). He is in the Editorial board of Computer Speech and Language (since 1988) and has been in the Editorial board of Computational Intelligence (1990- 2002), Pattern Recognition Letters (1980 - 2004), Signal Processing (1979-1989). He is author/editor of four books and more than 100 publications in international journals and conferences.
He has been Vice-President, Research Centre de recherche informatique de Montréal, Member then Chairman Natural Science and Engineering Research Council of Canada (NSERC) Computing and Information Sciences Grant Section Committee,.He has been member of Executive Advisory Board IBM Canada Toronto Research Lab, IEEE Speech technical committee, Scientific Council IM2 – Swiss Network of excellence, Canadian Chairs Review panel, Interdisciplinary Adjudication Committee (NSERC), Interdisciplinary Committee Canadian Foundation for Innovation, NSERC Strategic Grant Committee Communication and Computers Panel, Advisory Board Information Systems National Research Council of Canada, Scientific Council Centre National d'Etudes des Télécommunications, Lannion, France, Scientific Council CSELT Telecom Italy.
His research interest has been in spoken language processing, computer architecture, and software engineering. He is actually working on the extraction of semantic information from spoken documents.
Contact person regarding this talk: prof. Giuseppe Riccardi, segreteria-prof-riccardi [at] disi.unitn.it