Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Efthymios Tzinis"'
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 16:1329-1341
We present RemixIT, a simple yet effective self-supervised method for training speech enhancement without the need of a single isolated in-domain speech nor a noise waveform. Our approach overcomes limitations of previous methods which make them depe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2f2f3595c526cb16ebada347d75e0b8
https://doi.org/10.1109/jstsp.2022.3200911
https://doi.org/10.1109/jstsp.2022.3200911
Autor:
Martha-Spyridoula Katsarou, Aikaterini Karathanasopoulou, Angeliki Andrianopoulou, Vasileios Desiniotis, Efthymios Tzinis, Efthimios Dimitrakis, Maria Lagiou, Evangelia Charmandari, Michael Aschner, Aristeidis M. Tsatsakis, George P. Chrousos, Nikolaos Drakoulis
Publikováno v:
Frontiers in Genetics, Vol 9 (2018)
Genetic polymorphisms in β1-, β2- and β3-adrenergic receptors (β-ARs) have been associated with chronic non-communicable disorders, such as cardiovascular diseases, asthma, chronic obstructive pulmonary disease (COPD) and obesity, as well as β-a
Externí odkaz:
https://doaj.org/article/2b497bcd6dc3414c874e7724585d0556
Traditional source separation approaches train deep neural network models end-to-end with all the data available at once by minimizing the empirical risk on the whole training set. On the inference side, after training the model, the user fetches a s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d5a8968e3b9c42278f004186add99fdc
http://arxiv.org/abs/2211.11917
http://arxiv.org/abs/2211.11917
Autor:
Zhepei Wang, Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, Paris Smaragdis
In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without relying on labeled data. For this purpose, we propose adopting repres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6abc117901a213e1d3a21774a59e0fdb
http://arxiv.org/abs/2205.07390
http://arxiv.org/abs/2205.07390
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198359
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::27edc36f23676ec36b0cd088c2a518da
https://doi.org/10.1007/978-3-031-19836-6_21
https://doi.org/10.1007/978-3-031-19836-6_21
Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem. In this study, we provide a family of efficient neural network architectures f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fc2255da3d249b92fc7f51194901e4d7
http://arxiv.org/abs/2103.02644
http://arxiv.org/abs/2103.02644
We propose RemixIT, a simple and novel self-supervised training method for speech enhancement. The proposed method is based on a continuously self-training scheme that overcomes limitations from previous studies including assumptions for the in-domai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0bed4835e2c18d10a37de24980e824ad
Publikováno v:
ICASSP
Recent deep learning approaches have shown great improvement in audio source separation tasks. However, the vast majority of such work is focused on improving average separation performance, often neglecting to examine or control the distribution of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef9baebfb809c18f04d511ba2abfaa0d
http://arxiv.org/abs/2010.13228
http://arxiv.org/abs/2010.13228
Autor:
Ariel Frank, Emmanuel Vincent, Fabian-Robert Stöter, Mathieu Hu, Joris Cosentino, Manuel Pariente, Samuele Cornell, Sunit Sivasankaran, David Ditter, Efthymios Tzinis, Juan M. Martín-Doñas, Antoine Deleforge, Michel Olvera, Jens Heitkaemper
Publikováno v:
Interspeech 2020
Interspeech 2020, Oct 2020, Shanghai, China
INTERSPEECH
Interspeech 2020, Oct 2020, Shanghai, China
INTERSPEECH
This paper describes Asteroid, the PyTorch-based audio source separation toolkit for researchers. Inspired by the most successful neural source separation systems, it provides all neural building blocks required to build such a system. To improve rep
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7bd860f867da876db8feffc5d8aa9bd
https://inria.hal.science/hal-02962964/document
https://inria.hal.science/hal-02962964/document
Publikováno v:
ICASSP
Discriminative models for source separation have recently been shown to produce impressive results. However, when operating on sources outside of the training set, these models can not perform as well and are cumbersome to update. Classical methods l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2279396e854cf24e7c5f3ad108772f9a
https://doi.org/10.1109/icassp40776.2020.9053588
https://doi.org/10.1109/icassp40776.2020.9053588