Foto 7

Elenco Pubblicazioni - Publications (1380)

This paper investigates machine learning approaches toward the development of a speaker dependent keywords spotting system intended for users with speech disorders, in particular for those with dysarthria, i.e., a neuromotor speech impairment associated with…
The recent advances in language modeling significantly improved the generative capabilities of deep neural models: in 2019 OpenAI released GPT-2, a pre-trained language model that can autonomously generate coherent, non-trivial and human-like text samples. Since…
ABSTRACT Connected and autonomous vehicles run their control algorithms in dedicated on-board computing platforms, which will become obsolete long before the end of the life cycle of the vehicles, severely limiting the evolution of their…