1 code implementation • 23 Feb 2024 • Nathanaël Carraz Rakotonirina, Marco Baroni
Transformer-based language models (LMs) track contextual information through large, hard-coded input windows.
no code implementations • 1 Jun 2023 • Christiaan Jacobs, Nathanaël Carraz Rakotonirina, Everlyn Asiko Chimoto, Bruce A. Bassett, Herman Kamper
But in an in-the-wild test on Swahili radio broadcasts with actual hate speech keywords, the AWE model (using one minute of template data) is more robust, giving similar performance to an ASR system trained on 30 hours of labelled data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • 20 Feb 2023 • Nathanaël Carraz Rakotonirina, Roberto Dessì, Fabio Petroni, Sebastian Riedel, Marco Baroni
We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the same information.
no code implementations • 29 Sep 2021 • Elena Raponi, Nathanaël Carraz Rakotonirina, Jérémy Rapin, Olivier Teytaud, Carola Doerr
Machine learning has invaded various domains of computer science, including black-box optimization.
1 code implementation • 26 Aug 2021 • Nathanaël Carraz Rakotonirina
Convolutions operate only locally, thus failing to model global interactions.
Ranked #1 on Audio Super-Resolution on Voice Bank corpus (VCTK) (using extra training data)
1 code implementation • 21 Jan 2020 • Nathanaël Carraz Rakotonirina, Andry Rasoanaivo
Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is a perceptual-driven approach for single image super resolution that is able to produce photorealistic images.