Search

Showing total 4 results
Start Over Topic domain (software engineering)
4 results

1. Language recognition on unknown conditions: the LORIA-Inria-MULTISPEECH system for AP20-OLR Challenge

Author

Irina Illina, Raphaël Duroselle, Sahidullah, Denis Jouvet, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), Experiments presented in this paper were carried out using the Grid5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr). This work has been partly funded by the French Direction Genérale de l’Armement., Grid'5000, Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), and Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Channel (digital image), Computer science, Generalization, Speech recognition, 020206 networking & telecommunications, 02 engineering and technology, Regularization (mathematics), Bottleneck, Domain (software engineering), Task (project management), 030507 speech-language pathology & audiology, 03 medical and health sciences, Robustness (computer science), Language recognition, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], domain generalization, 0305 other medical science, Selection (genetic algorithm), channel mismatch
Abstract

International audience; We describe the LORIA-Inria-MULTISPEECH system submitted to the Oriental Language Recognition AP20-OLR Challenge. This system has been specifically designed to be robust to unknown conditions: channel mismatch (task 1) and noisy conditions (task 3). Three sets of studies have been carried out for elaborating the system: design of multilingual bottleneck features, selection of robust features by evaluating language recognition performance on an unobserved channel, and design of the final models with different loss functions which exploit channel diversity within the training set. Key factors for robustness to unknown conditions are data augmentation techniques, stochastic weight averaging, and regularization of TDNNs with domain robustness loss functions. The final system is the combination of four TDNNs using bottleneck features and one GMM using SDC-MFCC features. Within the AP20-OLR Challenge, it achieves the top performance for tasks 1 and 3 with a $C_{avg}$ of respectively 0.0239 and 0.0374. This validates the approach for generalization to unknown conditions.

Published
2021
Full Text
View/download PDF

2. Multi-fidelity modeling with different input domain definitions using Deep Gaussian Processes

Author

Nouredine Melab, El-Ghazali Talbi, Ali Hebbal, Mathieu Balesdent, Loïc Brevault, DTIS, ONERA, Université Paris Saclay [Palaiseau], ONERA-Université Paris-Saclay, Optimisation de grande taille et calcul large échelle (BONUS), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), and The work of Ali Hebbal is a funded by ONERA - The French Aerospace Lab and the University of Lille through a PhD thesis. This work is also part of two projects (HERACLES and MUFIN) funded by ONERA. The Experiments presented in this paper were carried out using the Grid’5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr).

Subjects
FOS: Computer and information sciences, Domain of a function, Computer Science - Machine Learning, Control and Optimization, Computer science, media_common.quotation_subject, 0211 other engineering and technologies, Fidelity, Machine Learning (stat.ML), 02 engineering and technology, Machine Learning (cs.LG), Domain (software engineering), symbols.namesake, 0203 mechanical engineering, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, multifidélité, modélisation bayésienne, Gaussian process, 021106 design practice & management, media_common, business.industry, Quantum Physics, Computer Graphics and Computer-Aided Design, Computer Science Applications, 020303 mechanical engineering & transports, Test case, Control and Systems Engineering, espace entree dimension variée, symbols, Global Positioning System, Engineering design process, business, Parametrization, Algorithm, Software, processus gaussien
Abstract

International audience; Multi-fidelity approaches combine different models built on a scarce but accurate data-set (high-fidelity data-set), and a large but approximate one (low-fidelity data-set) in order to improve the prediction accuracy. Gaussian Processes (GPs) are one of the popular approaches to exhibit the correlations between these different fidelity levels. Deep Gaussian Processes (DGPs) that are functional compositions of GPs have also been adapted to multi-fidelity using the Multi-Fidelity Deep Gaussian process model (MF-DGP). This model increases the expressive power compared to GPs by considering non-linear correlations between fidelities within a Bayesian framework. However, these multi-fidelity methods consider only the case where the inputs of the different fidelity models are defined over the same domain of definition (e.g., same variables, same dimensions). However, due to simplification in the modeling of the low-fidelity, some variables may be omitted or a different parametrization may be used compared to the high-fidelity model. In this paper, Deep Gaussian Processes for multi-fidelity (MF-DGP) are extended to the case where a different parametrization is used for each fidelity. The performance of the proposed multifidelity modeling technique is assessed on analytical test cases and on structural and aerodynamic real physical problems.

Published
2020
Full Text
View/download PDF

3. Paper microfluidics for nucleic acid amplification testing (NAAT) of infectious diseases

Author

Pierre Garneret, Patrick Tabeling, Beatrice Jacquelin, Fabrice Monti, Anavaj Sakuntabhai, Pierre Lafaye, Laura Magro, Aurélia Kwasiborski, Camille Escadafal, Jessica Vanhomwegen, Jean-Claude Manuguerra, Laboratoire Microfluidique, MEMS, Nanostructures (MMN), Ecole Superieure de Physique et de Chimie Industrielles de la Ville de Paris (ESPCI Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), Cellule d'Intervention Biologique d'Urgence - Laboratory for Urgent Response to Biological Threats (CIBU), Institut Pasteur [Paris], HIV, Inflammation et persistance, Génétique fonctionnelle des Maladies infectieuses - Functional Genetics of Infectious Diseases, Institut Pasteur [Paris]-Centre National de la Recherche Scientifique (CNRS), Ingénierie des Anticorps (plate-forme) - Antibody Engineering (Platform), Centre National de la Recherche Scientifique (CNRS)-Institut Pasteur [Paris], P. T., J. C. M. and P. L. initiated the collaboration. L. M., P. G., B. J. and C. E. prepared the manuscript with the assistance of P. T. L. M., F. M. and P. T. brought expertise on paper microfluidics and technological developments. J. C. M., A. S., C. E., A. K., J. V. and P. L. helped on more biological points of view: isothermal amplifications and sample preparations., Institut Pasteur [Paris] (IP), HIV, Inflammation et persistance - HIV, Inflammation and Persistence, and Institut Pasteur [Paris] (IP)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Paper, [SDV.BIO]Life Sciences [q-bio]/Biotechnology, Microfluidics, Biomedical Engineering, Loop-mediated isothermal amplification, Bioengineering, Nanotechnology, 02 engineering and technology, Biology, 01 natural sciences, Biochemistry, Communicable Diseases, law.invention, Domain (software engineering), law, [SDV.MHEP.MI]Life Sciences [q-bio]/Human health and pathology/Infectious diseases, Lab-On-A-Chip Devices, Nucleic Acid Amplification Tests, Humans, [SDV.MHEP.ME]Life Sciences [q-bio]/Human health and pathology/Emerging diseases, 010401 analytical chemistry, General Chemistry, Nucleic acid amplification technique, Equipment Design, Lab-on-a-chip, Microfluidic Analytical Techniques, 021001 nanoscience & nanotechnology, Data science, 0104 chemical sciences, 3. Good health, Molecular Diagnostic Techniques, Low and middle income countries, Nucleic acid, 0210 nano-technology, Nucleic Acid Amplification Techniques
Abstract

International audience; The diagnosis of infectious diseases is entering a new and interesting phase. Technologies based on paper microfluidics, coupled to developments in isothermal amplification of Nucleic Acids (NAs) raise opportunities for bringing the methods of molecular biology in the field, in a low setting environment. A lot of work has been performed in the domain over the last few years and the landscape of contributions is rich and diverse. Most often, the level of sample preparation differs, along with the sample nature, the amplification and detection methods, and the design of the device, among other features. In this review, we attempt to offer a structured description of the state of the art. The domain is not mature and there exist bottlenecks that hamper the realization of Nucleic Acid Amplification Tests (NAATs) complying with the constraints of the field in low and middle income countries. In this domain however, the pace of progress is impressively fast. This review is written for a broad Lab on a Chip audience.

Published
2017
Full Text
View/download PDF

4. Advancing Research on Categories for Institutional Approaches of Organizations

Author

Romain Boulongne, Rodolphe Durand, emlyon business school, Ecole des Hautes Etudes Commerciales (HEC Paris), HEC Research Paper Series, and Haldemann, Antoine

Subjects
050402 sociology, 050208 finance, media_common.quotation_subject, Field (Bourdieu), Perspective (graphical), 05 social sciences, Family resemblance, Cognition, Domain (software engineering), Epistemology, 0504 sociology, 0502 economics and business, Conceptual combination, Goal achievement, [SHS.GESTION]Humanities and Social Sciences/Business administration, Sociology, Function (engineering), [SHS.GESTION] Humanities and Social Sciences/Business administration, 050203 business & management, media_common
Abstract

In this chapter, we first review the two main approaches to categories (understood from a cognitive perspective) found in the current literature. The ecological and the goal-based approaches to categories vary in terms of premises (prototypes vs. ideals), processes (central tendency and family resemblance vs. conceptual combination and goal achievement), and economic and institutional consequences. We then present three modes of reconciliation between the two approaches (intra-audience, inter-audience and as a function of field evolution) and integrate them more broadly into the institutional literature. Finally, in the last section, we expose fruitful areas for future research: we account for the domain validity of each approach; emphasize ignored research avenues at the field, organizational and individual levels; and finally make stronger connections between category research and strategy research.

Published
2016