Access content directly

Mohamed Morchid

65
Documents

Presentation

Since september 2015, Dr. Mohamed Morchid is [**Associate Professor**](https://fr.wikipedia.org/wiki/Maître_de_conférences_(France)) in the Laboratoire Informatique d'Avignon (LIA) within the [University of Avignon](http://univ-avignon.fr), France and Ass. Prof. Mohamed Morchid has obtained the [**Habilitation à Diriger des Recherches (HDR) in computer sicence**](https://fr.wikipedia.org/wiki/Habilitation_universitaire#En_France) at november 26th 2019. He also gives different courses on computer science at the Centre d'Enseignement et de Recherche en Informatique (CERI) of the University of Avignon. The research interests of Dr. Mohamed Morchid lie on [**Artificial Intelligence (AI)**](https://en.wikipedia.org/wiki/Artificial_intelligence) with a special focus on deep neural networks with applications on [**Natural Language Processing (NLP)**](https://en.wikipedia.org/wiki/Natural_language_processing). From septembre 2014 to august 2015, Dr. Morchid has been an Teaching and Research Assistant within the [University of Avignon](http://univ-avignon.fr), France. He has pursued his research by proposing a robust representation of noisy documents from an automatic speech recognition system in a reduced space. Then, Ass. Prof. Morchid has proposed original methods based on topic models to locate short text messages from sharing platforms. From november 1st 2013 to febuary 1st 2014, Dr. Mohamed Morchid spents time visiting the [Microsoft Research](http://research.microsoft.com/en-us/labs/cambridge/) (Cambridge, UK) Laboratory and worked on the [PowerPoint Assistant](http://research.microsoft.com/apps/video/default.aspx?id=211308) international project. He has proposed original methods to allow Microsoft customers to enrich their PowerPoint presentations with relevant content. Mohamed Morchid has obtained at 25th november 2014 his Ph.D. in Computer Science within the LIA on Natural Language Processing (NLP), and more precisely, he has proposed robust representation of noisy documents from an automatic speech recognition system (dialogues) or from sharing platforms such as Twitter or Youtube. In addition, Dr. Mohamed Morchid serves as Associate Editor for [ IEEE/ACM Transactions on Audio, Speech and Language Processing](https://signalprocessingsociety.org/publications-resources/ieeeacm-transactions-audio-speech-and-language-processing/editorial-board) and as Action Editor for [ACL Rolling Review](https://www.aclweb.org/adminwiki/index.php?title=ACL_Rolling_Review_Proposal). You can find out more information at [mohamedmorchid.online.fr](/mohamedmorchid.online.fr).
Depuis septembre 2015, Dr. Mohamed Morchid est [ **Maître de Conférences**](https://fr.wikipedia.org/wiki/Maître_de_conférences_(France)) au sein de l'[Avignon Université](http://univ-avignon.fr) et il a soutenu son [**Habilitation à Diriger des Recherches (HDR) en Informatique**](https://fr.wikipedia.org/wiki/Habilitation_universitaire#En_France) le 26 novembre 2019. Ses travaux de recherche sont réalisés au Laboratoire Informatique d'Avignon (LIA) et son service statutaire est effectué au Centre d'Enseignement et de Recherche en Informatique (CERI) de l'Univeristé d'Avignon. Les thèmes de recherche de Dr. Mohamed Morchid s'articulent autour de l'[**Intelligence Artificielle (IA)**](https://fr.wikipedia.org/wiki/Intelligence_artificielle), et plus particulièrement, des réseaux de neurones profonds pour le [ **Traitement Automatique du Langage (TAL)**](https://fr.wikipedia.org/wiki/Traitement_automatique_du_langage_naturel). De septembre 2014 à août 2015, Mohamed Morchid a été Attaché Temporaire d'Enseignement et de Recherche (ATER) à l'[Université d'Avignon](http://univ-avignon.fr). Il a poursuivi, dans un premier temps, ses travaux pour une représentation robuste de documents parlés fortement bruités ainsi que pour la localisation automatique de documents issus du Web. Du 1er novembre 2013 au 1er fevrier 2014, Ass. Prof. Morchid a effectué un séjour de recherche au sein du laboratoire [Microsoft Research](http://research.microsoft.com/en-us/labs/cambridge/) sur le projet international de l'[Assistant PowerPoint](http://research.microsoft.com/apps/video/default.aspx?id=211308). Dans ce contexte, Dr. Mohamed Morchid a proposé des méthodes originales de traitement automatique du langage permettant aux utilisateurs d'enrichir leurs présentations PowerPoint avec du contenu informatif. Ass. Prof. Mohamed Morchid a obtenu le 25 novembre 2014 le doctorat en Informatique au sein du Laboratoire Informatique d'Avignon dans le domaine du traitement automatique du langage, et plus précisement, sur la représentation robuste de documents fortement bruités issus de transcriptions automatiques de douments parlés (dialogues) ou issus de plates-formes d'échange comme Twitter ou Youtube. De plus, Ass. Prof. Morchid est editeur associé pour le journal [IEEE/ACM Transactions on Audio, Speech and Language Processing](https://signalprocessingsociety.org/publications-resources/ieeeacm-transactions-audio-speech-and-language-processing/editorial-board) et "Action editor" pour [ACL Rolling Review](https://www.aclweb.org/adminwiki/index.php?title=ACL_Rolling_Review_Proposal). Plus d'information concernant ses travaux de recherche sont disponibles sur le site [mohamedmorchid.online.fr](http://mohamedmorchid.online.fr).

Publications

Image document

Real to H-space Autoencoders for Theme Identification in Telephone Conversations

Titouan Parcollet , Mohamed Morchid , Xavier Bost , Georges Linarès , Renato de Mori et al.
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, 28, pp.198-210. ⟨10.1109/TASLP.2019.2950596⟩
Journal articles hal-02402005v1

Denoised Bottleneck Features From Deep Autoencoders for Telephone Conversation Analysis

Killian Janod , Mohamed Morchid , Richard Dufour , Georges Linares , Renato de Mori et al.
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2017, 25 (9), pp.1809-1820. ⟨10.1109/TASLP.2017.2718843⟩
Journal articles hal-02356138v1
Image document

Automatic Text Summarization Approaches to Speed up Topic Model Learning Process

Mohamed Morchid , Juan-Manuel Torres-Moreno , Richard Dufour , Javier Ramírez-Rodríguez , Georges Linares et al.
International Journal of Computational Linguistics and Applications, 2016, 7, pp.87 - 109
Journal articles hal-02356467v1

A Topic Modeling based Representation to Detect Tweet Locations

Mohamed Morchid , Didier Josselin , Y. Portilla , R. Dufour , E. Altman et al.
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015, XL-3/W3, pp.629-634. ⟨10.5194/isprsarchives-XL-3-W3-629-2015⟩
Journal articles hal-01250548v1

Compact Multiview Representation of Documents Based on the Total Variability Space

Mohamed Morchid , Mohamed Bouallegue , Richard Dufour , Georges Linares , Driss Matrouf et al.
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2015, ⟨10.1109/TASLP.2015.2431854⟩
Journal articles hal-01319808v1
Image document

Total Variability Space for LDA-based multi-view text categorization

Mohamed Morchid , Mohamed Bouallegue , Richard Dufour , Georges Linarès , Renato de Mori et al.
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2015, ⟨10.1109/TASLP.2015.2431854⟩
Journal articles hal-01322940v1

An Author-Topic based Approach to Cluster Tweets and Mine their Location

Mohamed Morchid , Yonathan Portilla , Didier Josselin , Richard Dufour , Eitan Altman et al.
Procedia Environmental Sciences, 2015, 27, pp.26-29. ⟨10.1016/j.proenv.2015.07.109⟩
Journal articles hal-01251313v1

Feature selection using Principal Component Analysis for massive retweet detection

Mohamed Morchid , Richard Dufour , Pierre-Michel Bousquet , Georges Linares , Juan-Manuel Torres-Moreno et al.
Pattern Recognition Letters, 2014, ⟨10.1016/j.patrec.2014.05.020⟩
Journal articles hal-01319767v1
Image document

CGCNN: COMPLEX GABOR CONVOLUTIONAL NEURAL NETWORK ON RAW SPEECH

Paul-Gauthier Noé , Titouan Parcollet , Mohamed Morchid
ICASSP 2020, May 2020, Barcelona, Spain
Conference papers hal-02474746v1
Image document

E2E-SINCNET: TOWARD FULLY END-TO-END SPEECH RECOGNITION

Titouan Parcollet , Mohamed Morchid , Georges Linares
ICASSP, May 2020, Barcelone, Spain
Conference papers hal-02484600v1
Image document

M2H-GAN: A GAN-based Mapping from Machine to Human Transcripts for Speech Understanding

Titouan Parcollet , Mohamed Morchid , Xavier Bost , Georges Linarès
INTERSPEECH 2019, Sep 2019, Gratz, Austria
Conference papers hal-02107674v2
Image document

Quaternion Recurrent Neural Networks

Titouan Parcollet , Mirco Ravanelli , Mohamed Morchid , Georges Linarès , Chiheb Trabelsi et al.
ICLR 2019, May 2019, Nouvelle Orléans, United States
Conference papers hal-02107628v1
Image document

Real to H-space Encoder for Speech Recognition

Titouan Parcollet , Mohamed Morchid , Georges Linarès , Renato de Mori
INTERSPEECH 2019, Jun 2019, Graz, Austria
Conference papers hal-02158201v1
Image document

Quaternion convolutional neural networks for heterogeneous image processing

Titouan Parcollet , Mohamed Morchid , Georges Linarès
IEEE ICASSP, May 2019, Brighton, United Kingdom
Conference papers hal-02107644v1

Réseaux de neurones convolutifs de quaternions pour l'identification de thèmes de conversations téléphoniques

Titouan Parcollet , Mohamed Morchid , Georges Linares
CORIA 2019, Mar 2019, Lyon, France
Conference papers hal-02107663v1

Quaternion Convolutional Neural Networks For Theme Identification Of Telephone Conversations

Titouan Parcollet , Mohamed Morchid , Georges Linares , Renato de Mori
2018 IEEE Spoken Language Technology Workshop (SLT), Dec 2018, Athens, Greece. pp.685-691
Conference papers hal-02107660v1
Image document

Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition

Titouan Parcollet , Ying Zhang , Mohamed Morchid , Chiheb Trabelsi , Georges Linarès et al.
Interspeech 2018, Sep 2018, HYDERABAD, India. pp.22-26, ⟨10.21437/Interspeech.2018-1898⟩
Conference papers hal-02107611v1
Image document

Speech Recognition with Quaternion Neural Networks

Titouan Parcollet , Mirco Ravanelli , Mohamed Morchid , Georges Linares , Renato de Mori et al.
NIPS 2018 - IRASL Workshop, Dec 2018, Montréal, Canada
Conference papers hal-02107651v1
Image document

Quaternion Denoising Encoder-Decoder for Theme Identification of Telephone Conversations

Titouan Parcollet , Mohamed Morchid , Georges Linarès
Interspeech 2017, Aug 2017, Stockholm, Sweden. pp.3325-3328, ⟨10.21437/Interspeech.2017-1029⟩
Conference papers hal-02107632v1

Réseaux de neurones de quaternions pour le traitement du langage.

Titouan Parcollet , Mohamed Morchid , Georges Linares
CORIA 2017, Mar 2017, Marseille, France
Conference papers hal-02107655v1
Image document

Deep quaternion neural networks for spoken language understanding

Titouan Parcollet , Mohamed Morchid , Georges Linarès
2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Dec 2017, Okinawa, Japan. pp.504-511
Conference papers hal-02107630v1

Deep Stacked Autoencoders for Spoken Language Understanding

Killian Janod , Mohamed Morchid , Richard Dufour , Georges Linares , Renato De Mori et al.
Interspeech 2016, Sep 2016, San Francisco, United States. pp.720-724, ⟨10.21437/Interspeech.2016-63⟩
Conference papers hal-02356395v1

Quaternion Neural Networks for Spoken Language Understanding

Titouan Parcollet , Mohamed Morchid , Pierre-Michel Bousquet Bousquet , Richard Dufour , Georges Linarès et al.
2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.362-368
Conference papers hal-02107532v1

A log-linear weighting approach in the Word2vec space for spoken language understanding

Janod Killian , Mohamed Morchid , Richard Dufour , Georges Linares
2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.356-361, ⟨10.1109/SLT.2016.7846289⟩
Conference papers hal-02356406v1

Tracking dialog states using an Author-Topic based representation

Richard Dufour , Mohamed Morchid , Titouan Parcollet
2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.544-551
Conference papers hal-02107641v1

Parallel Long Short-Term Memory for multi-stream classification

Mohamed Bouaziz , Mohamed Morchid , Richard Dufour , Georges Linares , Renato de Mori et al.
2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.218-223, ⟨10.1109/SLT.2016.7846268⟩
Conference papers hal-02356410v1
Image document

Spoken Language Understanding in a Latent Topic-based Subspace

Mohamed Morchid , Mohamed Bouaziz , Waad Ben Kheder , Killian Janod , Pierre-Michel Bousquet Bousquet et al.
Interspeech 2016, Sep 2016, San Francisco, United States. ⟨10.21437/Interspeech.2016-50⟩
Conference papers hal-02356390v1

Improving multi-stream classification by mapping sequence-embedding in a high dimensional space

Mohamed Bouaziz , Mohamed Morchid , Richard Dufour , Georges Linares
2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.224-231, ⟨10.1109/SLT.2016.7846269⟩
Conference papers hal-02356420v1

Topic-space based setup of a neural network for theme identification of highly imperfect transcriptions

Mohamed Morchid , Richard Dufour , Georges Linarès
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) , Dec 2015, Scottsdale, United States. ⟨10.1109/ASRU.2015.7404815⟩
Conference papers hal-01339956v1

Utilisation d'annotations sémantiques pour la validation automatique d'hypothèses dans des conversations téléphoniques

Carole Lailler , Yannick Estève , Renato de Mori , Mohamed Bouallègue , Mohamed Morchid et al.
TALN 2015, 2015, Caen, France
Conference papers hal-01433216v1

Integration of word and semantic features for theme identification in telephone conversations

Yannick Estève , Mohamed Bouallegue , Carole Lailler , Mohamed Morchid , Richard Dufour et al.
6th International Workshop on Spoken Dialog Systems (IWSDS 2015), 2015, Busan, South Korea
Conference papers hal-01433213v1
Image document

A Comparison of Normalization Techniques Applied to Latent Space Representations for Speech Analytics

Mohamed Morchid , Richard Dufour , Driss Matrouf
Interspeech 2015, Sep 2015, Dresden, Germany
Conference papers hal-02356373v1

Latent Topic Model Based Representations for a Robust Theme Identification of Highly Imperfect Automatic Transcriptions

Mohamed Morchid , Richard Dufour , Georges Linares , Youssef Hamadi
16th International Conference, CICLing 2015, Apr 2015, Le Caire, Egypt. ⟨10.1007/978-3-319-18117-2_44⟩
Conference papers hal-01293908v1

Author-topic based representation of call-center conversations

Mohamed Morchid , Richard Dufour , Mohamed Bouallegue , Georges Linarès
IEEE Spoken Language Technology Workshop (SLT) , Dec 2014, South Lake Tahoe United States. ⟨10.1109/SLT.2014.7078577⟩
Conference papers hal-01318662v1

Getting by with a Little Help from the Crowd: Practical Approaches to Social Image Labeling

Babak Loni , Jonathon Hare , Mihai Georgescu , Michael Riegler , Xiaofei Zhu et al.
CrowdMM '14 International ACM Workshop on Crowdsourcing for Multimedia , Nov 2014, Orlando, United States. ⟨10.1145/2660114.2660123⟩
Conference papers hal-01318338v1

Subspace Gaussian Mixture Models for Dialogues Classification

Mohamed Bouallegue , Mohamed Morchid , Richard Dufour , Driss Matrouf , Georges Linarès et al.
Interspeech, May 2014, Singapore, Singapore
Conference papers hal-01313132v1
Image document

A Topic-Based Approach for Post-processing Correction of Automatic Translations

Mohamed Morchid , Stéphane Huet , Richard Dufour
11th International Workshop on Spoken Language Translation (IWSLT), 2014, South Lake Tahoe, NV, United States
Conference papers hal-02021817v1

Improving dialogue classification using a topic space representation and a Gaussian classifier based on the decision rule

Mohamed Morchid , Richard Dufour , Pierre-Michel Bousquet , Mohamed Bouallegue , Georges Linarès et al.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2014, Florence, Italy. ⟨10.1109/ICASSP.2014.6853571⟩
Conference papers hal-01318674v1

Classification de transcriptions automatiques imparfaites : Doit-on adapter le calcul du taux d'erreur-mot ?

Mohamed Morchid , Richard Dufour , Georges Linares , Renato de Mori
JEP, Jun 2014, Le Mans, France
Conference papers hal-01319782v1

A LDA-Based Topic Classification Approach from Highly Imperfect Automatic Transcriptions

Mohamed Morchid , Richard Dufour , Georges Linarès
LREC, May 2014, Reykjavik, Iceland
Conference papers hal-01319771v1

Sumacc Project's Corpus: A Topic-based Query Extention Approach to Retrieve Multimedia Documents

Mohamed Morchid , Richard Dufour , Usman Niaz , Francis Bouvier , Clément de Groc et al.
17th International Conference, TSD, Sep 2014, Brno, Czech Republic
Conference papers hal-01319787v1

An I-vector Based Approach to Compact Multi-Granularity Topic Spaces Representation of Textual Documents

Mohamed Morchid , Mohamed Bouallegue , Richard Dufour , Georges Linarès , Driss Matrouf et al.
the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),, Oct 2014, Doha, Qatar. ⟨10.3115/v1/D14-1051⟩
Conference papers hal-01318651v1

Factor Analysis based Semantic Variability Compensation for Automatic Conversation Representation

Mohamed Bouallegue , Mohamed Morchid , Richard Dufour , Driss Matrouf , Georges Linarès et al.
Interspeech, May 2014, Singapore, Singapore
Conference papers hal-01313121v1

I-vector based Representation of Highly Imperfect Automatic Transcriptions

Mohamed Morchid , Mohamed Bouallegue , Richard Dufour , Georges Linarès , Driss Matrouf et al.
INTERSPEECH, May 2014, Singapore, Singapore
Conference papers hal-01318657v1

Theme Identification in Human-Human Conversations with Features from Specific Speaker Type Hidden Spaces

Mohamed Morchid , Richard Dufour , Mohamed Bouallegue , Georges Linarès , Renato de Mori et al.
INTERSPEECH, May 2014, Singapore, Singapore
Conference papers hal-01318666v1

A COMBINED THEMATIC AND ACOUSTIC APPROACH FOR A MUSIC RECOMMENDATION SERVICE IN TV COMMERCIALS

Mohamed Morchid , Richard Dufour , Georges Linarès
ISMIR, Oct 2014, Tapei, Taiwan
Conference papers hal-01319769v1

Characterizing and Predicting Bursty Events: The Buzz Case Study on Twitter

Mohamed Morchid , Georges Linarès , Richard Dufour
LREC, May 2014, Reykjavik, Iceland
Conference papers hal-01319806v1

Thematic Representation of Short Text Messages with Latent Topics: Application in the Twitter context

Mohamed Morchid , Richard Dufour , Georges Linarès
PACLING 2013, Sep 2013, Tokyo, Japan
Conference papers hal-01319779v1
Image document

Systèmes du LIA à DEFT'13

Xavier Bost , Ilaria Brunetti , Luis Adrian Cabrera Diego , Jean-Valère Cossu , Andréa Carneiro Linhares et al.
DEFT2013, Jun 2013, Les Sables d'Olonne, France
Conference papers hal-01313065v1

LIA @ MediaEval 2013 Spoken Web Search Task: An I-Vector based Approach

Mohamed Bouallegue , Grégory Senay , Mohamed Morchid , Driss Matrouf , Georges Linares et al.
MediaEval, Oct 2013, Barcelone, Spain
Conference papers hal-01313144v1

Event detection from image hosting services by slightly-supervised multi-span context models

Mohamed Morchid , Richard Dufour , Georges Linarès
2013 11TH INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI), Jun 2013, VESZPREM,, Hungary. ⟨10.1109/CBMI.2013.6576563⟩
Conference papers hal-01318645v1

Prédiction des buzz sur Twitter

Mohamed Morchid , Georges Linares
CORIA, Apr 2013, Neuchâtel, Suisse
Conference papers hal-01319791v1
Image document

LIA@RepLab 2013

Jean Valère Cossu , Benjamin Bigot , Ludovic Bonnefoy , Mohamed Morchid , Xavier Bost et al.
Replab: An evaluation campaign for Online Reputation Management Systems, Fourth International Conference of the CLEF initiative, Sep 2013, Valencia, Spain
Conference papers hal-01967853v1

Theme Identification in Telephone Service Conversations using Quaternions of Speech Features

Mohamed Morchid , Georges Linarès , Marc El Bèze , Renato de Mori
Interspeech 2013, Aug 2013, Lyon, France
Conference papers hal-01339930v1

LIA @ MediaEval 2013 MusiClef Task: A Combined Thematic and Acoustic Approach

Mohamed Morchid , Richard Dufour , Mohamed Bouallegue , Georges Linares , Driss Matrouf et al.
MediaEval, Oct 2013, Barcelone, Spain
Conference papers hal-01318668v1

A LDA-based method for automatic tagging of Youtube videos

Mohamed Morchid , Georges Linares
14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) , Jul 2013, Paris, France. ⟨10.1109/WIAMIS.2013.6616126⟩
Conference papers hal-01319775v1

Combinaison de thèmes latents pour la contextualisation de Tweets

Mohamed Morchid , Richard Dufour , Georges Linarès
EGC'2013 13e Conférence Francophone sur l'Extraction et la Gestion des connaissances, Jan 2013, Toulouse, France
Conference papers hal-01339909v1

LIA @ MediaEval 2013 Crowdsourcing Task: Metadata or not Metadata? That is a Fashion Question

Mohamed Morchid , Richard Dufour , Mohamed Bouallegue , Georges Linares , Driss Matrouf et al.
MediaEval, Oct 2013, Barcelone, Spain
Conference papers hal-01318659v1

INEX 2012 Benchmark A semantic space for Tweet contextualization

Mohamed Morchid , Georges Linarès
INEX'12, Sep 2012, Rome, Italy
Conference papers hal-01319799v1

Extraction de mots-clefs dans des vidéos Web par Analyse Latente de Dirichlet

Mohamed Morchid , Georges Linares
TALN 2012, Jun 2012, Grenoble, France
Conference papers hal-01319794v1

Mediaeval benchmark: Social Event Detection using LDA and external resources

Mohamed Morchid , Georges Linarès
MediaEval, Sep 2011, Pise, Italy
Conference papers hal-01319802v1
Image document

Neural Networks for Natural Language Processing

Mohamed Morchid
Artificial Intelligence [cs.AI]. Avignon Université, 2019
Habilitation à diriger des recherches tel-02398814v2