Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Zinemanas, Pablo"'
Autor:
Alonso-Jiménez, Pablo, Pepino, Leonardo, Batlle-Roca, Roser, Zinemanas, Pablo, Bogdanov, Dmitry, Serra, Xavier, Rocamora, Martín
We present PECMAE, an interpretable model for music audio classification based on prototype learning. Our model is based on a previous method, APNet, which jointly learns an autoencoder and a prototypical network. Instead, we propose to decouple both
Externí odkaz:
http://arxiv.org/abs/2402.09318
Most recent work in visual sound source localization relies on semantic audio-visual representations learned in a self-supervised manner, and by design excludes temporal information present in videos. While it proves to be effective for widely used b
Externí odkaz:
http://arxiv.org/abs/2211.08367
Autor:
Fuentes, Magdalena, Salamon, Justin, Zinemanas, Pablo, Rocamora, Martín, Paja, Genís, Román, Irán R., Miron, Marius, Serra, Xavier, Bello, Juan Pablo
Soundata is a Python library for loading and working with audio datasets in a standardized way, removing the need for writing custom loaders in every project, and improving reproducibility by providing tools to validate data against a canonical versi
Externí odkaz:
http://arxiv.org/abs/2109.12690
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Most recent work in visual sound source localization relies on semantic audio-visual representations learned in a self-supervised manner, and by design excludes temporal information present in videos. While it proves to be effective for widely used b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5fdae5c2c686b087ae03015b40f86cc7
https://doi.org/10.1109/icassp49357.2023.10094965
https://doi.org/10.1109/icassp49357.2023.10094965
Comunicació presentada a: DCASE 2021 celebrat del 15 al 19 de novembre de 2021 de manera virtual. Understanding the reasons behind the predictions of deep neural networks is a pressing concern as it can be critical in several application scenarios.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1610::e9dbd45dc507aedc63788cbc534cba78
http://hdl.handle.net/10230/49196
http://hdl.handle.net/10230/49196
Publikováno v:
COLIBRI
Universidad de la República
instacron:Universidad de la República
Universidad de la República
instacron:Universidad de la República
This paper describes the efforts we devoted to improve Ambisonics decoders in Csound. Current version of the existing opcode, namely bformdec1, has some limitations that should be surpassed in order that the decoders better fulfill the Ambisonics cri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c503d98cb2eb773bf9886a492e5b7f59
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Zinemanas, Pablo, Hounie, Ignacio, Cancela, Pablo, Font Corbera, Frederic, Rocamora, Martín, Serra, Xavier
Comunicació presentada a: 5th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2020) celebrat el 2 i 3 de novembre de 2020 a Tòquio, Japó. This document presents DCASE-models, an open–source Python library for rapid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1610::5a613c945d64da29b2a1ac4483ab1f0d
http://hdl.handle.net/10230/45641
http://hdl.handle.net/10230/45641
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2016 IEEE 7th Latin American Symposium on Circuits & Systems (LASCAS); 2016, p79-82, 4p