Skip to Main content
Number of documents

67

Mohamed Morchid - Associate Professor - HDR

Since september 2015, I am an Associate Professor in the Laboratoire Informatique d'Avignon (LIA) within the University of Avignon, France and I have obtained the Habilitation à Diriger des Recherches (HDR) in computer sicence at november 26th 2019. I also give different courses on computer science at the Centre d'Enseignement et de Recherche en Informatique (CERI) of the University of Avignon. 

My research interests lie on Artificial Intelligence (AI) with a special focus on Artificial Neural Networks. The application contexts are Natural Language Processing (NLP), Information Retrieval, image processing as well as Information Extraction from big corpora of documents (Web). 

From septembre 2014 to august 2015, I have been an Teaching and Research Assistant within the University of Avignon, France. I have pursued my research by proposing a robust representation of noisy documents from an automatic speech recognition system in a reduced space. Then, I have proposed original methods based on topic models to locate short text messages from sharing platforms.

From november 1st 2013 to febuary 1st 2014, I spent time visiting the Microsoft Research (Cambridge, UK) Laboratory and worked on the PowerPoint Assistant international project. I proposed original methods to allow Microsoft customers to enrich their PowerPoint presentations with relevant content.

I have obtained at 25th november 2014, my Ph.D. in Computer Science within the Laboratoire Informatique d'Avignon in the Natural Language Processing (NLP) domain, and more precisely, I have proposed robust representation of noisy documents from an automatic speech recognition system (dialogues) or from sharing platforms such as Twitter or Youtube.

You can find out more information related to my research in section here.

Journal articles8 documents

  • Titouan Parcollet, Mohamed Morchid, Xavier Bost, Georges Linarès, Renato de Mori. Real to H-space Autoencoders for Theme Identification in Telephone Conversations. IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2020, 28, pp.198-210. ⟨10.1109/TASLP.2019.2950596⟩. ⟨hal-02402005⟩
  • Killian Janod, Mohamed Morchid, Richard Dufour, Georges Linares, Renato de Mori. Denoised Bottleneck Features From Deep Autoencoders for Telephone Conversation Analysis. IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2017, 25 (9), pp.1809-1820. ⟨10.1109/TASLP.2017.2718843⟩. ⟨hal-02356138⟩
  • Mohamed Morchid, Juan-Manuel Torres-Moreno, Richard Dufour, Javier Ramírez-Rodríguez, Georges Linares. Automatic Text Summarization Approaches to Speed up Topic Model Learning Process. International Journal of Computational Linguistics and Applications, Alexander Gelbukh, 2016, 7, pp.87 - 109. ⟨hal-02356467⟩
  • Mohamed Morchid, Mohamed Bouallegue, Richard Dufour, Georges Linarès, Renato de Mori. Total Variability Space for LDA-based multi-view text categorization. IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2015, ⟨10.1109/TASLP.2015.2431854⟩. ⟨hal-01322940⟩
  • Mohamed Morchid, Yonathan Portilla, Didier Josselin, Richard Dufour, Eitan Altman, et al.. An Author-Topic based Approach to Cluster Tweets and Mine their Location. Procedia Environmental Sciences, Elsevier, 2015, 27, pp.26-29. ⟨10.1016/j.proenv.2015.07.109⟩. ⟨hal-01251313⟩
  • Mohamed Morchid, Didier Josselin, Y. Portilla, R. Dufour, E. Altman, et al.. A Topic Modeling based Representation to Detect Tweet Locations: Example of the event "Je suis Charlie". International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH (Copernicus Publications), 2015, XL-3/W3, pp.629-634. ⟨10.5194/isprsarchives-XL-3-W3-629-2015⟩. ⟨hal-01250548⟩
  • Mohamed Morchid, Mohamed Bouallegue, Richard Dufour, Georges Linares, Driss Matrouf, et al.. Compact Multiview Representation of Documents Based on the Total Variability Space. IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2015, ⟨10.1109/TASLP.2015.2431854⟩. ⟨hal-01319808⟩
  • Mohamed Morchid, Richard Dufour, Pierre-Michel Bousquet, Georges Linares, Juan-Manuel Torres-Moreno. Feature selection using Principal Component Analysis for massive retweet detection. Pattern Recognition Letters, Elsevier, 2014, ⟨10.1016/j.patrec.2014.05.020⟩. ⟨hal-01319767⟩

Conference papers55 documents

  • Paul-Gauthier Noé, Titouan Parcollet, Mohamed Morchid. CGCNN: COMPLEX GABOR CONVOLUTIONAL NEURAL NETWORK ON RAW SPEECH. ICASSP 2020, May 2020, Barcelona, Spain. ⟨hal-02474746⟩
  • Titouan Parcollet, Mohamed Morchid, Georges Linares. E2E-SINCNET: TOWARD FULLY END-TO-END SPEECH RECOGNITION. ICASSP, May 2020, Barcelone, Spain. ⟨hal-02484600⟩
  • Titouan Parcollet, Mohamed Morchid, Georges Linares. Réseaux de neurones convolutifs de quaternions pour l'identification de thèmes de conversations téléphoniques. CORIA 2019, Mar 2019, Lyon, France. ⟨hal-02107663⟩
  • Titouan Parcollet, Mohamed Morchid, Georges Linarès, Renato de Mori. Real to H-space Encoder for Speech Recognition. INTERSPEECH 2019, Jun 2019, Graz, Austria. ⟨hal-02158201⟩
  • Titouan Parcollet, Mirco Ravanelli, Mohamed Morchid, Georges Linarès, Chiheb Trabelsi, et al.. Quaternion Recurrent Neural Networks. ICLR 2019, May 2019, Nouvelle Orléans, United States. ⟨hal-02107628⟩
  • Titouan Parcollet, Mohamed Morchid, Xavier Bost, Georges Linarès. M2H-GAN: A GAN-based Mapping from Machine to Human Transcripts for Speech Understanding. INTERSPEECH 2019, Sep 2019, Gratz, Austria. ⟨hal-02107674v2⟩
  • Titouan Parcollet, Mohamed Morchid, Georges Linarès. Quaternion convolutional neural networks for heterogeneous image processing. IEEE ICASSP, May 2019, Brighton, United Kingdom. ⟨hal-02107644⟩
  • Titouan Parcollet, Mohamed Morchid, Georges Linares, Renato de Mori. Quaternion Convolutional Neural Networks For Theme Identification Of Telephone Conversations. 2018 IEEE Spoken Language Technology Workshop (SLT), Dec 2018, Athens, Greece. pp.685-691. ⟨hal-02107660⟩
  • Titouan Parcollet, Ying Zhang, Mohamed Morchid, Chiheb Trabelsi, Georges Linarès, et al.. Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition. Interspeech 2018, Sep 2018, HYDERABAD, India. pp.22-26, ⟨10.21437/Interspeech.2018-1898⟩. ⟨hal-02107611⟩
  • Titouan Parcollet, Mirco Ravanelli, Mohamed Morchid, Georges Linares, Renato de Mori. Speech Recognition with Quaternion Neural Networks. NIPS 2018 - IRASL Workshop, Dec 2018, Montréal, Canada. ⟨hal-02107651⟩
  • Titouan Parcollet, Mohamed Morchid, Georges Linares. Réseaux de neurones de quaternions pour le traitement du langage.. CORIA 2017, Mar 2017, Marseille, France. ⟨hal-02107655⟩
  • Titouan Parcollet, Mohamed Morchid, Georges Linarès. Deep quaternion neural networks for spoken language understanding. 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Dec 2017, Okinawa, Japan. pp.504-511. ⟨hal-02107630⟩
  • Titouan Parcollet, Mohamed Morchid, Georges Linarès. Quaternion Denoising Encoder-Decoder for Theme Identification of Telephone Conversations. Interspeech 2017, Aug 2017, Stockholm, Sweden. pp.3325-3328, ⟨10.21437/Interspeech.2017-1029⟩. ⟨hal-02107632⟩
  • Mohamed Bouaziz, Mohamed Morchid, Richard Dufour, Georges Linares. Improving multi-stream classification by mapping sequence-embedding in a high dimensional space. 2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.224-231, ⟨10.1109/SLT.2016.7846269⟩. ⟨hal-02356420⟩
  • Mohamed Morchid, Mohamed Bouaziz, Waad Kheder, Killian Janod, Pierre-Michel Bousquet, et al.. Spoken Language Understanding in a Latent Topic-based Subspace. Interspeech 2016, Sep 2016, San Francisco, United States. ⟨10.21437/Interspeech.2016-50⟩. ⟨hal-02356390⟩
  • Killian Janod, Mohamed Morchid, Richard Dufour, Georges Linares, Renato De Mori. Deep Stacked Autoencoders for Spoken Language Understanding. Interspeech 2016, Sep 2016, San Francisco, United States. pp.720-724, ⟨10.21437/Interspeech.2016-63⟩. ⟨hal-02356395⟩
  • Janod Killian, Mohamed Morchid, Richard Dufour, Georges Linares. A log-linear weighting approach in the Word2vec space for spoken language understanding. 2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.356-361, ⟨10.1109/SLT.2016.7846289⟩. ⟨hal-02356406⟩
  • Mohamed Bouaziz, Mohamed Morchid, Richard Dufour, Georges Linares, Renato de Mori. Parallel Long Short-Term Memory for multi-stream classification. 2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.218-223, ⟨10.1109/SLT.2016.7846268⟩. ⟨hal-02356410⟩
  • Titouan Parcollet, Mohamed Morchid, Pierre-Michel Bousquet, Richard Dufour, Georges Linarès, et al.. Quaternion Neural Networks for Spoken Language Understanding. 2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.362-368. ⟨hal-02107532⟩
  • Richard Dufour, Mohamed Morchid, Titouan Parcollet. Tracking dialog states using an Author-Topic based representation. 2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.544-551. ⟨hal-02107641⟩
  • Mohamed Morchid, Richard Dufour, Georges Linarès. Topic-space based setup of a neural network for theme identification of highly imperfect transcriptions. 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) , Dec 2015, Scottsdale, United States. ⟨10.1109/ASRU.2015.7404815⟩. ⟨hal-01339956⟩
  • Mohamed Morchid, Richard Dufour, Driss Matrouf. A Comparison of Normalization Techniques Applied to Latent Space Representations for Speech Analytics. Interspeech 2015, Sep 2015, Dresden, Germany. ⟨hal-02356373⟩
  • Mohamed Morchid, Richard Dufour, Georges Linares, Youssef Hamadi. Latent Topic Model Based Representations for a Robust Theme Identification of Highly Imperfect Automatic Transcriptions. 16th International Conference, CICLing 2015, Apr 2015, Le Caire, Egypt. ⟨10.1007/978-3-319-18117-2_44⟩. ⟨hal-01293908⟩
  • Yannick Estève, Mohamed Bouallegue, Carole Lailler, Mohamed Morchid, Richard Dufour, et al.. Integration of word and semantic features for theme identification in telephone conversations. 6th International Workshop on Spoken Dialog Systems (IWSDS 2015), 2015, Busan, South Korea. ⟨hal-01433213⟩
  • Carole Lailler, Yannick Estève, Renato de Mori, Mohamed Bouallègue, Mohamed Morchid. Utilisation d'annotations sémantiques pour la validation automatique d'hypothèses dans des conversations téléphoniques. TALN 2015, 2015, Caen, France. ⟨hal-01433216⟩
  • Mohamed Bouallegue, Mohamed Morchid, Richard Dufour, Driss Matrouf, Georges Linarès, et al.. Factor Analysis based Semantic Variability Compensation for Automatic Conversation Representation. Interspeech, May 2014, Singapore, Singapore. ⟨hal-01313121⟩
  • Mohamed Morchid, Richard Dufour, Georges Linarès. A LDA-Based Topic Classification Approach from Highly Imperfect Automatic Transcriptions. LREC, May 2014, Reykjavik, Iceland. ⟨hal-01319771⟩
  • Mohamed Morchid, Richard Dufour, Georges Linarès. A COMBINED THEMATIC AND ACOUSTIC APPROACH FOR A MUSIC RECOMMENDATION SERVICE IN TV COMMERCIALS. ISMIR, Oct 2014, Tapei, Taiwan. ⟨hal-01319769⟩
  • Mohamed Morchid, Richard Dufour, Mohamed Bouallegue, Georges Linarès, Renato de Mori. Theme Identification in Human-Human Conversations with Features from Specific Speaker Type Hidden Spaces. INTERSPEECH, May 2014, Singapore, Singapore. ⟨hal-01318666⟩
  • Mohamed Morchid, Richard Dufour, Mohamed Bouallegue, Georges Linarès. Author-topic based representation of call-center conversations. IEEE Spoken Language Technology Workshop (SLT) , Dec 2014, South Lake Tahoe United States. ⟨10.1109/SLT.2014.7078577⟩. ⟨hal-01318662⟩
  • Mohamed Morchid, Mohamed Bouallegue, Richard Dufour, Georges Linarès, Driss Matrouf, et al.. I-vector based Representation of Highly Imperfect Automatic Transcriptions. INTERSPEECH, May 2014, Singapore, Singapore. ⟨hal-01318657⟩
  • Mohamed Morchid, Mohamed Bouallegue, Richard Dufour, Georges Linarès, Driss Matrouf, et al.. An I-vector Based Approach to Compact Multi-Granularity Topic Spaces Representation of Textual Documents. the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),, Oct 2014, Doha, Qatar. ⟨10.3115/v1/D14-1051⟩. ⟨hal-01318651⟩
  • Mohamed Morchid, Richard Dufour, Georges Linares, Renato de Mori. Classification de transcriptions automatiques imparfaites : Doit-on adapter le calcul du taux d'erreur-mot ?. JEP, Jun 2014, Le Mans, France. ⟨hal-01319782⟩
  • Mohamed Morchid, Richard Dufour, Pierre-Michel Bousquet, Mohamed Bouallegue, Georges Linarès, et al.. Improving dialogue classification using a topic space representation and a Gaussian classifier based on the decision rule. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2014, Florence, Italy. ⟨10.1109/ICASSP.2014.6853571⟩. ⟨hal-01318674⟩
  • Mohamed Bouallegue, Mohamed Morchid, Richard Dufour, Driss Matrouf, Georges Linarès, et al.. Subspace Gaussian Mixture Models for Dialogues Classification. Interspeech, May 2014, Singapore, Singapore. ⟨hal-01313132⟩
  • Babak Loni, Jonathon Hare, Mihai Georgescu, Michael Riegler, Xiaofei Zhu, et al.. Getting by with a Little Help from the Crowd: Practical Approaches to Social Image Labeling. CrowdMM '14 International ACM Workshop on Crowdsourcing for Multimedia , Nov 2014, Orlando, United States. ⟨10.1145/2660114.2660123⟩. ⟨hal-01318338⟩
  • Mohamed Morchid, Richard Dufour, Usman Niaz, Francis Bouvier, Clément de Groc, et al.. Sumacc Project's Corpus: A Topic-based Query Extention Approach to Retrieve Multimedia Documents. 17th International Conference, TSD, Sep 2014, Brno, Czech Republic. ⟨hal-01319787⟩
  • Mohamed Morchid, Stéphane Huet, Richard Dufour. A Topic-Based Approach for Post-processing Correction of Automatic Translations. 11th International Workshop on Spoken Language Translation (IWSLT), 2014, South Lake Tahoe, NV, United States. ⟨hal-02021817⟩
  • Mohamed Morchid, Georges Linarès, Richard Dufour. Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter. LREC, May 2014, Reykjavik, Iceland. ⟨hal-01319806⟩
  • Mohamed Morchid, Richard Dufour, Georges Linarès. Combinaison de thèmes latents pour la contextualisation de Tweets. EGC'2013 13e Conférence Francophone sur l'Extraction et la Gestion des connaissances, Jan 2013, Toulouse, France. ⟨hal-01339909⟩
  • Mohamed Morchid, Georges Linarès, Marc El Bèze, Renato de Mori. Theme Identification in Telephone Service Conversations using Quaternions of Speech Features. Interspeech 2013, Aug 2013, Lyon, France. ⟨hal-01339930⟩
  • Mohamed Morchid, Georges Linarès, Marc El Bèze, Renato de Mori. Theme Identification in Telephone Service Conversations using Quaternions of Speech Features. Interspeech 2013, Aug 2013, Lyon, France. ⟨hal-01339936⟩
  • Mohamed Morchid, Georges Linares. A LDA-based method for automatic tagging of Youtube videos. 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) , Jul 2013, Paris, France. ⟨10.1109/WIAMIS.2013.6616126⟩. ⟨hal-01319775⟩
  • Xavier Bost, Ilaria Brunetti, Luis Adrian Cabrera Diego, Jean-Valère Cossu, Andréa Linhares, et al.. Systèmes du LIA à DEFT'13. DEFT2013, Jun 2013, Les Sables d'Olonne, France. ⟨hal-01313065⟩
  • Mohamed Morchid, Georges Linares. A LDA-based method for automatic tagging of Youtube videos. 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), Jul 2013, Paris, France. ⟨10.1109/WIAMIS.2013.6616126⟩. ⟨hal-01319788⟩
  • Mohamed Morchid, Richard Dufour, Georges Linarès. Thematic Representation of Short Text Messages with Latent Topics: Application in the Twitter context. PACLING 2013, Sep 2013, Tokyo, Japan. ⟨hal-01319779⟩
  • Mohamed Morchid, Richard Dufour, Mohamed Bouallegue, Georges Linares, Driss Matrouf. LIA @ MediaEval 2013 MusiClef Task: A Combined Thematic and Acoustic Approach. MediaEval, Oct 2013, Barcelone, Spain. ⟨hal-01318668⟩
  • Mohamed Morchid, Richard Dufour, Mohamed Bouallegue, Georges Linares, Driss Matrouf. LIA @ MediaEval 2013 Crowdsourcing Task: Metadata or not Metadata? That is a Fashion Question. MediaEval, Oct 2013, Barcelone, Spain. ⟨hal-01318659⟩
  • Mohamed Morchid, Georges Linares. Prédiction des buzz sur Twitter. CORIA, Apr 2013, Neuchâtel, Suisse. ⟨hal-01319791⟩
  • Mohamed Bouallegue, Grégory Senay, Mohamed Morchid, Driss Matrouf, Georges Linares, et al.. LIA @ MediaEval 2013 Spoken Web Search Task: An I-Vector based Approach. MediaEval, Oct 2013, Barcelone, Spain. ⟨hal-01313144⟩
  • Jean Valère Cossu, Benjamin Bigot, Ludovic Bonnefoy, Mohamed Morchid, Xavier Bost, et al.. LIA@RepLab 2013. Replab: An evaluation campaign for Online Reputation Management Systems, Fourth International Conference of the CLEF initiative, Sep 2013, Valencia, Spain. ⟨hal-01967853⟩
  • Mohamed Morchid, Richard Dufour, Georges Linarès. Event detection from image hosting services by slightly-supervised multi-span context models. 2013 11TH INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI), Jun 2013, VESZPREM,, Hungary. ⟨10.1109/CBMI.2013.6576563⟩. ⟨hal-01318645⟩
  • Mohamed Morchid, Georges Linarès. INEX 2012 Benchmark A semantic space for Tweet contextualization. INEX'12, Sep 2012, Rome, Italy. ⟨hal-01319799⟩
  • Mohamed Morchid, Georges Linares. Extraction de mots-clefs dans des vidéos Web par Analyse Latente de Dirichlet. TALN 2012, Jun 2012, Grenoble, France. ⟨hal-01319794⟩
  • Mohamed Morchid, Georges Linarès. Mediaeval benchmark: Social Event Detection using LDA and external resources. MediaEval, Sep 2011, Pise, Italy. ⟨hal-01319802⟩

Poster communications1 document

  • Mohamed Morchid, Yonathan Portilla, Didier Josselin, Richard Dufour, Eitan Altman, et al.. An Author-Topic based Approach to Cluster Tweets and Mine their Location. Spatial Statistics 2015, Jun 2015, Avignon, France. ⟨hal-01250549⟩

Preprints, Working Papers, ...1 document

  • Cecilia Darnault, Titouan Parcollet, Mohamed Morchid. Artificial Intelligence: A Tale of Social Responsibility. 2019. ⟨hal-02270410v2⟩

Theses1 document

Habilitation à diriger des recherches1 document

  • Mohamed Morchid. Neural Networks for Natural Language Processing. Artificial Intelligence [cs.AI]. Avignon Université, 2019. ⟨tel-02398814v2⟩