index - GETALP Access content directly

Here is the updated scientific production of the GETALP research team (Study Group for Machine Translation and Automated Processing of Languages and Speech), part of the research area "Data and Knowledge Processing at Large Scale" within the LIG, Grenoble Informatics Laboratory.

The goal of the GETALP is to contribute significantly to the emergence of ubilingual computing, in the context of the development of ubiquitous computiing. This goal requires to carry out researches, often pluridisciplinary, in computer sciences, in linguistics and psycholinguistics, in semantics (link with ontologies), in pragmatics (for the dialogue), and in signal and speech processing.

The GETALP team is organized around six main research topics:

  1. Machine Translation (MT) and Computer-Aided Translation (CAT)
  2. Natural Language Processing (NLP) and associated platforms
  3. Linguistic Data Resources Collection and Construction
  4. Information Systems Localization
  5. Automatic Recognition of Speech, Speakers, Sounds and Dialect
  6. Sounds analysis and Interaction within Perceptive Environments

The activities linked to these research topics share five challenges:


LIG website


Voice-user interface Forensic voice comparison Assistance à la vie autonome Communication Alternative et Augmentée Wolof Speech recognition TAL Spoken language understanding Apprentissage profond Apprentissage machine Natural language understanding Dictionary Lexical database French Traduction automatique Machine learning Categst2i LSTM Ambient Intelligence Habitat intelligent L2 English Ambient Assisted Living Classification Apprentissage automatique LMF Machine translation Modèle acoustique Analyse morphologique Markov Logic Network Natural Language Processing Active learning Corpus Reconnaissance automatique de la parole Ambient Assisted Living AAL Affective Computing Spontaneous speech Pictogrammes Langues peu dotées Word Embedding Traduction automatique neuronale Speech Comprehensibility Reconnaissance Rhythm Under-resourced languages Language documentation Automatic Speech Recognition Language model Reconnaissance de sons Jibiki NLP Natural language processing Unwritten languages Smart Home Word Sense Disambiguation Speaker recognition Automatic speech recognition ASR Collaborative annotation Data collection Elderly Affective computing Human-computer interaction Comparable corpora Emotion recognition Désambiguïsation lexicale Ambient intelligence Base lexicale Activity Recognition Computational language documentation BERT Augmentative and Alternative Communication Machine Learning Détection-de-sons MotÀMot Expressive speech Natural language generation Active reading African languages Statistical machine translation Arabizi Extraction de contenu Assessment Locuteur Traduction Automatique DiLAF Bambara Lexical stress Challenge Machine Translation Lexique XML Français Neural machine translation Évaluation Quality estimation Deep learning Smart home Information Retrieval Arabic Dialect


Latest Publications