User profiles for A. Coucke
Alice CouckeHead of machine learning research at Sonos, Inc. Verified email at sonos.com Cited by 1446 |
Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces
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 …
solution to perform Spoken Language Understanding on microprocessors typical of IoT …
Federated learning for keyword spotting
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. …
with continuously running embedded speech-based models such as wake word detectors. …
Efficient keyword spotting using dilated convolutions and gating
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 …
spotting as opposed to recurrent networks that model long-term temporal dependencies …
ACE: adaptive cluster expansion for maximum entropy graphical model inference
Motivation: Graphical models are often employed to interpret patterns of correlations
observed in data through a network of interactions between the variables. Recently, Ising/Potts …
observed in data through a network of interactions between the variables. Recently, Ising/Potts …
Spoken language understanding on the edge
We consider the problem of performing Spoken Language Understanding (SLU) on small
devices typical of IoT applications. Our contribution is two-fold. First, we outline the design of …
devices typical of IoT applications. Our contribution is two-fold. First, we outline the design of …
Direct coevolutionary couplings reflect biophysical residue interactions in proteins
Coevolution of residues in contact imposes strong statistical constraints on the sequence
variability between homologous proteins. Direct-Coupling Analysis (DCA), a global statistical …
variability between homologous proteins. Direct-Coupling Analysis (DCA), a global statistical …
A treatment planning inter-comparison of proton and intensity modulated photon radiotherapy
…, J Debus, C Dykstra, PA Tercier, PA Coucke… - Radiotherapy and …, 1999 - Elsevier
Purpose: A comparative treatment planning study has been undertaken between standard
photon delivery techniques,b intensity modulated photon methods and spot scanned protons …
photon delivery techniques,b intensity modulated photon methods and spot scanned protons …
Inference of compressed Potts graphical models
We consider the problem of inferring a graphical Potts model on a population of variables.
This inverse Potts problem generally involves the inference of a large number of parameters, …
This inverse Potts problem generally involves the inference of a large number of parameters, …
Primary non‐Hodgkin's lymphoma of the nasal cavity: prognostic significance of paranasal extension and the role of radiotherapy and chemotherapy
YX Li, PA Coucke, JY Li, DZ Gu, XF Liu… - … Journal of the …, 1998 - Wiley Online Library
BACKGROUND This study was conducted to determine whether the paranasal extension of
a primary non‐Hodgkin's lymphoma (NHL) of the nasal cavity has any deleterious effect on …
a primary non‐Hodgkin's lymphoma (NHL) of the nasal cavity has any deleterious effect on …
Small footprint text-independent speaker verification for embedded systems
…, R Tavarone, M Poumeyrol, A Coucke - ICASSP 2021-2021 …, 2021 - ieeexplore.ieee.org
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 …
computational requirements of State-Of-The-Art (SOTA) systems make them unsuited for …