Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Kaloga, Yacouba"'
Recently proposed automatic pathological speech detection approaches rely on spectrogram input representations or wav2vec2 embeddings. These representations may contain pathology irrelevant uncorrelated information, such as changing phonetic content
Externí odkaz:
http://arxiv.org/abs/2409.17276
Despite the promising performance of state of the art approaches for Parkinsons Disease (PD) detection, these approaches often analyze individual speech segments in isolation, which can lead to suboptimal results. Dysarthric cues that characterize sp
Externí odkaz:
http://arxiv.org/abs/2409.07884
The choice of good distances and similarity measures between objects is important for many machine learning methods. Therefore, many metric learning algorithms have been developed in recent years, mainly for Euclidean data in order to improve perform
Externí odkaz:
http://arxiv.org/abs/2209.12727
We present a novel multiview canonical correlation analysis model based on a variational approach. This is the first nonlinear model that takes into account the available graph-based geometric constraints while being scalable for processing large sca
Externí odkaz:
http://arxiv.org/abs/2010.16132
We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literature: i) The model is inductive: it can embed new graphs without re-trai
Externí odkaz:
http://arxiv.org/abs/2007.03373
Publikováno v:
Phys. Rev. Lett. 124, 248006 (2020)
We sandwich a colloidal gel between two parallel plates and induce a radial flow by lifting the upper plate at a constant velocity. Two distinct scenarios result from such a tensile test: ($i$) stable flows during which the gel undergoes a tensile de
Externí odkaz:
http://arxiv.org/abs/2002.06744
Autor:
Kaloga, Yacouba
Publikováno v:
Intelligence artificielle [cs.AI]. Université de Lyon, 2021. Français. ⟨NNT : 2021LYSEN086⟩
Machine learning has become a popular research topic in recent years, thanks to the reintroduction of neural networks in the early 2010s. The abundance of data and computational power at that time allowed for very good performance in a variety of lea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c37ac1896fbb96bf83ad824f6693cb62
https://theses.hal.science/tel-03610111/file/KALOGA_Yacouba_2021LYSEN086_These.pdf
https://theses.hal.science/tel-03610111/file/KALOGA_Yacouba_2021LYSEN086_These.pdf
Autor:
Kaloga, Yacouba, Borgnat, Pierre, Chepuri, Sundeep Prabhakar, Abry, Patrice, Habrard, Amaury, Chepuri, Sundeep
Publikováno v:
Signal Processing
Signal Processing, Elsevier, 2021, 188, pp.108182. ⟨10.1016/j.sigpro.2021.108182⟩
Signal Processing, 2021, 188, pp.108182. ⟨10.1016/j.sigpro.2021.108182⟩
Signal Processing, Elsevier, 2021, 188, pp.108182. ⟨10.1016/j.sigpro.2021.108182⟩
Signal Processing, 2021, 188, pp.108182. ⟨10.1016/j.sigpro.2021.108182⟩
International audience; We present a novel approach for multiview canonical correlation analysis based on a variational graph neural network model. We propose a nonlinear model which takes into account the available graph-based geometric constraints
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2bd341651ee6275b487f3c847e2d4601
https://hal.archives-ouvertes.fr/hal-03436007/file/GPCCAv3.pdf
https://hal.archives-ouvertes.fr/hal-03436007/file/GPCCAv3.pdf
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.