Search Results for author: Alice Coucke

Found 8 papers, 6 papers with code

Small footprint Text-Independent Speaker Verification for Embedded Systems

no code implementations3 Nov 2020 Julien Balian, Raffaele Tavarone, Mathieu Poumeyrol, Alice Coucke

Deep neural network approaches to speaker verification have proven successful, but typical computational requirements of State-Of-The-Art (SOTA) systems make them unsuited for embedded applications.

Text-Independent Speaker Verification

Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems

1 code implementation3 Nov 2020 Stéphane d'Ascoli, Alice Coucke, Francesco Caltagirone, Alexandre Caulier, Marc Lelarge

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation.

Data Augmentation Language Modelling +2

Conditioned Query Generation for Task-Oriented Dialogue Systems

1 code implementation9 Nov 2019 Stéphane d'Ascoli, Alice Coucke, Francesco Caltagirone, Alexandre Caulier, Marc Lelarge

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation.

Task-Oriented Dialogue Systems Text Generation

Efficient keyword spotting using dilated convolutions and gating

4 code implementations19 Nov 2018 Alice Coucke, Mohammed Chlieh, Thibault Gisselbrecht, David Leroy, Mathieu Poumeyrol, Thibaut Lavril

We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states.

Small-Footprint Keyword Spotting

Federated Learning for Keyword Spotting

1 code implementation9 Oct 2018 David Leroy, Alice Coucke, Thibaut Lavril, Thibault Gisselbrecht, Joseph Dureau

We propose a practical approach based on federated learning to solve out-of-domain issues with continuously running embedded speech-based models such as wake word detectors.

Federated Learning Keyword Spotting

Deep Representation for Patient Visits from Electronic Health Records

no code implementations26 Mar 2018 Jean-Baptiste Escudié, Alaa Saade, Alice Coucke, Marc Lelarge

We show how to learn low-dimensional representations (embeddings) of patient visits from the corresponding electronic health record (EHR) where International Classification of Diseases (ICD) diagnosis codes are removed.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.