collaborators

10 papers

cs.CL2026

Benchmarking Speech-to-Speech Translation Models

Alkis Koudounas, Hayato Futami, Quentin Jodelet +3

Speech-to-speech translation (S2ST) has advanced rapidly, but offline evaluation lacks a unified protocol: studies report non-overlapping metric subsets, preventing direct comparis…

cs.CL2025

FAME: Fictional Actors for Multilingual Erasure

Claudio Savelli, Moreno La Quatra, Alkis Koudounas +1

LLMs trained on web-scale data raise concerns about privacy and the right to be forgotten. To address these issues, Machine Unlearning provides techniques to remove specific inform…

cs.CL2025

Hallucination Benchmark for Speech Foundation Models

Alkis Koudounas, Moreno La Quatra, Manuel Giollo +2

Hallucinations in automatic speech recognition (ASR) systems refer to fluent and coherent transcriptions produced by neural ASR models that are completely unrelated to the underlyi…

eess.AS2025

A Concept-based approach to Voice Disorder Detection

Davide Ghia, Gabriele Ciravegna, Alkis Koudounas +4

Voice disorders affect a significant portion of the population, and the ability to diagnose them using automated, non-invasive techniques would represent a substantial advancement…

cs.CL2025

"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding

Alkis Koudounas, Moreno La Quatra, Eliana Pastor +2

Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional neural architectures, yet their application to speech processing remains under exp…

cs.CL2025

Exploring Generative Error Correction for Dysarthric Speech Recognition

Moreno La Quatra, Alkis Koudounas, Valerio Mario Salerno +1

Despite the remarkable progress in end-to-end Automatic Speech Recognition (ASR) engines, accurately transcribing dysarthric speech remains a major challenge. In this work, we prop…