no code implementations • 25 Jan 2024 • Pier Paolo Tricomi, Luca Pajola, Luca Pasa, Mauro Conti
In this work, we investigate the relationship between Spotify users' attributes and their public playlists.
no code implementations • 10 Jun 2021 • Luca Pasa, Nicolò Navarin, Wolfgang Erb, Alessandro Sperduti
Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago.
no code implementations • 1 Jan 2021 • Luca Pasa, Nicolò Navarin, Alessandro Sperduti
In this paper, we propose a different strategy, considering a single graph convolution layer that independently exploits neighbouring nodes at different topological distances, generating decoupled representations for each of them.
no code implementations • 5 Dec 2019 • Ander Arriandiaga, Giovanni Morrone, Luca Pasa, Leonardo Badino, Chiara Bartolozzi
In order to overcome this limitation, we propose the use of event-driven cameras and exploit compression, high temporal resolution and low latency, for low cost and low latency motion feature extraction, going towards online embedded audio-visual speech processing.
no code implementations • 16 Apr 2019 • Luca Pasa, Giovanni Morrone, Leonardo Badino
In this paper, we analyzed how audio-visual speech enhancement can help to perform the ASR task in a cocktail party scenario.
1 code implementation • 6 Nov 2018 • Giovanni Morrone, Luca Pasa, Vadim Tikhanoff, Sonia Bergamaschi, Luciano Fadiga, Leonardo Badino
In this paper, we address the problem of enhancing the speech of a speaker of interest in a cocktail party scenario when visual information of the speaker of interest is available.
Ranked #1 on Speech Enhancement on GRID corpus (mixed-speech)
no code implementations • NeurIPS 2014 • Luca Pasa, Alessandro Sperduti
We propose a pre-training technique for recurrent neural networks based on linear autoencoder networks for sequences, i. e. linear dynamical systems modelling the target sequences.