297 citations · 357 across the 10 of their papers we have counts for
12 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
Sonos Voice Control Bias Assessment Dataset: A Methodology for Demographic Bias Assessment in Voice Assistants
Chloé Sekkat, Fanny Leroy, Salima Mdhaffar +4
Recent works demonstrate that voice assistants do not perform equally well for everyone, but research on demographic robustness of speech technologies is still scarce. This is main…
Conditioned Text Generation with Transfer for Closed-Domain Dialogue Systems
Stéphane d'Ascoli, Alice Coucke, Francesco Caltagirone +2
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. An alternative s…
Small footprint Text-Independent Speaker Verification for Embedded Systems
Julien Balian, Raffaele Tavarone, Mathieu Poumeyrol +1
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 embe…
Conditioned Query Generation for Task-Oriented Dialogue Systems
Stéphane d'Ascoli, Alice Coucke, Francesco Caltagirone +2
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. An alternative s…
Inference of compressed Potts graphical models
Francesca Rizzato, Alice Coucke, Eleonora de Leonardis +4
We consider the problem of inferring a graphical Potts model on a population of variables, with a non-uniform number of Potts colors (symbols) across variables. This inverse Potts…
Efficient keyword spotting using dilated convolutions and gating
Alice Coucke, Mohammed Chlieh, Thibault Gisselbrecht +3
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…
Spoken Language Understanding on the Edge
Alaa Saade, Alice Coucke, Alexandre Caulier +9
We consider the problem of performing Spoken Language Understanding (SLU) on small devices typical of IoT applications. Our contributions are twofold. First, we outline the design…
Federated Learning for Keyword Spotting
David Leroy, Alice Coucke, Thibaut Lavril +2
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. We con…
Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
Alice Coucke, Alaa Saade, Adrien Ball +9
This paper presents the machine learning architecture of the Snips Voice Platform, a software solution to perform Spoken Language Understanding on microprocessors typical of IoT de…
Deep Representation for Patient Visits from Electronic Health Records
Jean-Baptiste Escudié, Alaa Saade, Alice Coucke +1
We show how to learn low-dimensional representations (embeddings) of patient visits from the corresponding electronic health record (EHR) where International Classification of Dise…
An interplay of migratory and division forces as a generic mechanism for stem cell patterns
Edouard Hannezo, Alice Coucke, Jean-François Joanny
In many adult tissues, stem cells and differentiated cells are not homogeneously distributed : stem cells are arranged in periodic "niches", and differentiated cells are constantly…