Luca de Alfaro — accepted AI-conference papers

2024

Prioritizing Data Acquisition for end-to-end Speech Model Improvement

Alkis Koudounas, Eliana Pastor, Giuseppe Attanasio, Luca de Alfaro, Elena Baralis

ICASSP 2024accepted

As speech processing moves toward more data-hungry models, data selection and acquisition become crucial to building better systems. Recent efforts have championed quantity over quality, following the mantra "The more data, the better." However, not every data brings the same benefit. This paper pro…

Cited by 0 Source ↗Scholar ↗

2023

Exploring Subgroup Performance in End-to-End Speech Models

Alkis Koudounas, Eliana Pastor, Giuseppe Attanasio, Vittorio Mazzia, Manuel Giollo, Thomas Gueudré +4

ICASSP 2023accepted

End-to-End Spoken Language Understanding models are generally evaluated according to their overall accuracy, or separately on (a priori defined) data subgroups of interest. We propose a technique for analyzing model performance at the subgroup level, which considers all subgroups that can be defined…

Cited by 0 Source ↗Scholar ↗