Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Riad, Rachid"'
Autor:
de Gennes, Marc, Lesage, Adrien, Denais, Martin, Cao, Xuan-Nga, Chang, Simon, Van Remoortere, Pierre, Dakhlia, Cyrille, Riad, Rachid
Non-invasive methods for diagnosing mental health conditions, such as speech analysis, offer promising potential in modern medicine. Recent advancements in machine learning, particularly speech foundation models, have shown significant promise in det
Externí odkaz:
http://arxiv.org/abs/2409.19042
Parts of the brain that carry sensory tasks are organized topographically: nearby neurons are responsive to the same properties of input signals. Thus, in this work, inspired by the neuroscience literature, we proposed a new topographic inductive bia
Externí odkaz:
http://arxiv.org/abs/2211.13152
Convolutional neural networks typically contain several downsampling operators, such as strided convolutions or pooling layers, that progressively reduce the resolution of intermediate representations. This provides some shift-invariance while reduci
Externí odkaz:
http://arxiv.org/abs/2202.01653
Autor:
Chenain, Lucie, Riad, Rachid, Fraisse, Nicolas, Jubin, Cécilia, Morgado, Graça, Youssov, Katia, Lunven, Marine, Bachoud-Levi, Anne-Catherine
Publikováno v:
In Cortex July 2024 176:144-160
Deep Learning models have become potential candidates for auditory neuroscience research, thanks to their recent successes on a variety of auditory tasks. Yet, these models often lack interpretability to fully understand the exact computations that h
Externí odkaz:
http://arxiv.org/abs/2103.07125
Autor:
Riad, Rachid, Titeux, Hadrien, Lemoine, Laurie, Montillot, Justine, Sliwinski, Agnes, Bagnou, Jennifer Hamet, Cao, Xuan Nga, Bachoud-Lévi, Anne-Catherine, Dupoux, Emmanuel
Conversations between a clinician and a patient, in natural conditions, are valuable sources of information for medical follow-up. The automatic analysis of these dialogues could help extract new language markers and speed-up the clinicians' reports.
Externí odkaz:
http://arxiv.org/abs/2010.16131
Autor:
Riad, Rachid, Titeux, Hadrien, Lemoine, Laurie, Montillot, Justine, Bagnou, Jennifer Hamet, Cao, Xuan Nga, Dupoux, Emmanuel, Bachoud-Lévi, Anne-Catherine
Disease-modifying treatments are currently assessed in neurodegenerative diseases. Huntington's Disease represents a unique opportunity to design automatic sub-clinical markers, even in premanifest gene carriers. We investigated phonatory impairments
Externí odkaz:
http://arxiv.org/abs/2006.05365
Autor:
Titeux, Hadrien, Riad, Rachid, Cao, Xuan-Nga, Hamilakis, Nicolas, Madden, Kris, Cristia, Alejandrina, Bachoud-Lévi, Anne-Catherine, Dupoux, Emmanuel
Publikováno v:
LREC 2020 - 12th Language Resources and Evaluation Conference, May 2020, Marseille, France. pp.6976-6982
We introduce Seshat, a new, simple and open-source software to efficiently manage annotations of speech corpora. The Seshat software allows users to easily customise and manage annotations of large audio corpora while ensuring compliance with the for
Externí odkaz:
http://arxiv.org/abs/2003.01472
Disfluent speech has been previously addressed from two main perspectives: the clinical perspective focusing on diagnostic, and the Natural Language Processing (NLP) perspective aiming at modeling these events and detect them for downstream tasks. In
Externí odkaz:
http://arxiv.org/abs/2003.01018
Autor:
Riad, Rachid, Dancette, Corentin, Karadayi, Julien, Zeghidour, Neil, Schatz, Thomas, Dupoux, Emmanuel
Recent studies have investigated siamese network architectures for learning invariant speech representations using same-different side information at the word level. Here we investigate systematically an often ignored component of siamese networks: t
Externí odkaz:
http://arxiv.org/abs/1804.11297