PhD defence, Sahar GHANNAY Title : A study of continuous word representations applied to ASR error detection. Composition of the jury : Présidente : Martine Adda-Decker, Reviewers : Sophie Rosset, Frédéric Béchet, Examiners : Benoit Favre, Benjamin Lecouteux, Supervisor : Yannick Estève Co-supervisor : Nathalie Camelin Abstract : This thesis concerns a study of continuous […]
Deep neural networks for oral and written language processingStarting: 04/09/2017PhD Student: Antoine CaubrièreAdvisor(s): Yannick Estève (LIUM, LST)Co-advisor(s): Antoine Laurent (LIUM, LST) & Emmanuel Morin (LS2N)Funding: RAPACE ProjectThe aim of this thesis is to develop a named entity recognition system in an audio stream that will rely solely on a deep neural network. Until now, this […]
Towards a hybrid approach for Arabic Sentiment AnalysisStarting: 03/10/2016PhD Student: Amira BarhoumiAdvisor(s): Yannick Estève (LIUM, LST)Co-advisor(s): Nathalie Camelin (LIUM, LST) & Lamia Hadrich Belguith (MIRACL, Tunisie)Funding: Agreement “Cotutelle Convention” (LIUM, LST) & (MIRACL, Tunisie)Sentiment analysis is a growing field of research and has been subject of numerous studies. This thesis aims at designing a hybrid […]
Corpus: TED-LIUM Release 3Licence: Creative Commons BY-NC-ND 3.0 (attribution/non-commercial/no-derivatives)Author(s): François FernandezVincent NguyenSahar GhannayNatalia TomashenkoYannick EstèveThis is the TED-LIUM corpus release 3, licensed under Creative Commons BY-NC-ND 3.0 (http://creativecommons.org/licenses/by-nc-nd/3.0/deed.en). All talks and text are property of TED Conferences LLC. This new TED-LIUM release was made through a collaboration between the Ubiqus company and the […]
Corpus: TED-LIUM Release 2Licence: Creative Commons BY-NC-ND 3.0 (attribution/non-commercial/no-derivatives)Author(s): Anthony RousseauPaul DelégliseYannick EstèveThis is the TED-LIUM corpus release 2, licensed under Creative Commons BY-NC-ND 3.0 (http://creativecommons.org/licenses/by-nc-nd/3.0/deed.en). The TED-LIUM corpus was made from audio talks and their transcriptions available on the TED website. We have prepared and filtered these data in order to train acoustic […]
Corpus: TED-LIUM Release 1Licence: Creative Commons BY-NC-ND 3.0 (attribution/non-commercial/no-derivatives)Author(s): Anthony RousseauPaul DelégliseYannick EstèveThis is the TED-LIUM corpus release 1, licensed under Creative Commons BY-NC-ND 3.0 (http://creativecommons.org/licenses/by-nc-nd/3.0/deed.en). The TED-LIUM corpus is English-language TED talks, with transcriptions, sampled at 16kHz. It contains about 118 hours of speech. More details are given in this paper: A. […]
Software: NMTPYLicence: MIT LicenseGitHub: https://github.com/lium-lst/nmtpyURL: https://arxiv.org/abs/1706.00457Author(s): Ozan CaglayanMercedes García MartínezAdrien BardetWalid AransaLoïc BarraultFethi Bougaresnmtpy is a suite of Python tools, primarily based on the starter code provided in dl4mt-tutorial for training neural machine translation networks using Theano. The basic motivation behind forking dl4mt-tutorial was to create a framework where it would be easy to implement […]
Software: NMTPYTORCHLicence: MIT LicenseGitHub: https://github.com/lium-lst/nmtpytorch/URL: https://arxiv.org/abs/1706.00457Author(s): Ozan CaglayanMercedes García MartínezAdrien BardetWalid AransaFethi BougaresLoïc BarraultThis is the PyTorch fork of nmtpy, a sequence-to-sequence framework which was originally a fork of dl4mt-tutorial.
Software: LIUM Speaker DiarizationLicence: GPLURL: https://projets-lium.univ-lemans.fr/spkdiarization/Outil de segmentation et regroupement locuteur (Speaker diarization) en java.
Software: SIDEKITLicence: LGPLGitHub: https://git-lium.univ-lemans.fr/Larcher/sidekitURL: https://projets-lium.univ-lemans.fr/sidekit/Author(s): Anthony LarcherKong Aik LeeSylvain Meignier Welcome to SIDEKIT documentation! SIDEKIT is an open source package for Speaker and Language recognition. The aim of SIDEKIT is to provide an educational and efficient toolkit for speaker/language recognition including the whole chain of treatment that goes from the audio data to the analysis […]
Français