no code implementations • 5 Feb 2024 • Luca Della Libera, Cem Subakan, Mirco Ravanelli
The increasing success of deep neural networks has raised concerns about their inherent black-box nature, posing challenges related to interpretability and trust.
1 code implementation • 2 Feb 2024 • Luca Della Libera, Jacopo Andreoli, Davide Dalle Pezze, Mirco Ravanelli, Gian Antonio Susto
In particular, we show through experimental studies on simulated run-to-failure turbofan engine degradation data that Bayesian deep learning models trained via Stein variational gradient descent consistently outperform with respect to convergence speed and predictive performance both the same models trained via parametric variational inference and their frequentist counterparts trained via backpropagation.
1 code implementation • 25 Oct 2023 • Luca Della Libera, Pooneh Mousavi, Salah Zaiem, Cem Subakan, Mirco Ravanelli
To the best of our knowledge, CL-MASR is the first continual learning benchmark for the multilingual ASR task.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 19 Jun 2022 • Luca Della Libera, Cem Subakan, Mirco Ravanelli, Samuele Cornell, Frédéric Lepoutre, François Grondin
Transformers have recently achieved state-of-the-art performance in speech separation.
no code implementations • 14 Nov 2019 • Luca Della Libera
On the contrary, Bayesian deep learning has recently emerged as a promising solution to account for uncertainty in the training process, achieving state-of-the-art performance in many classification and regression tasks.
no code implementations • 31 Oct 2019 • Luca Della Libera, Vladimir Golkov, Yue Zhu, Arman Mielke, Daniel Cremers
Convolutional networks are successful due to their equivariance/invariance under translations.