5 papers
Benchmarking Representations for Speech, Music, and Acoustic Events
Moreno La Quatra, Alkis Koudounas, Lorenzo Vaiani +4
Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We presen…
Houston we have a Divergence: A Subgroup Performance Analysis of ASR Models
Alkis Koudounas, Flavio Giobergia
The Fearless Steps APOLLO Community Resource provides unparalleled opportunities to explore the potential of multi-speaker team communications from NASA Apollo missions. This study…
MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection
Federico Borra, Claudio Savelli, Giacomo Rosso +2
In Natural Language Generation (NLG), contemporary Large Language Models (LLMs) face several challenges, such as generating fluent yet inaccurate outputs and reliance on fluency-ce…
Reconstructing Atmospheric Parameters of Exoplanets Using Deep Learning
Flavio Giobergia, Alkis Koudounas, Elena Baralis
Exploring exoplanets has transformed our understanding of the universe by revealing many planetary systems that defy our current understanding. To study their atmospheres, spectros…
Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features
Eliana Pastor, Alkis Koudounas, Giuseppe Attanasio +2
Recent advances in eXplainable AI (XAI) have provided new insights into how models for vision, language, and tabular data operate. However, few approaches exist for understanding s…