6 papers
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…
"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…
MVP: Multi-source Voice Pathology detection
Alkis Koudounas, Moreno La Quatra, Gabriele Ciravegna +6
Voice disorders significantly impact patient quality of life, yet non-invasive automated diagnosis remains under-explored due to both the scarcity of pathological voice data, and t…
DeepDialogue: A Multi-Turn Emotionally-Rich Spoken Dialogue Dataset
Alkis Koudounas, Moreno La Quatra, Elena Baralis
Recent advances in conversational AI have demonstrated impressive capabilities in single-turn responses, yet multi-turn dialogues remain challenging for even the most sophisticated…
"Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
Alkis Koudounas, Claudio Savelli, Flavio Giobergia +1
Machine unlearning, the process of efficiently removing specific information from machine learning models, is a growing area of interest for responsible AI. However, few studies ha…
voc2vec: A Foundation Model for Non-Verbal Vocalization
Alkis Koudounas, Moreno La Quatra, Marco Sabato Siniscalchi +1
Speech foundation models have demonstrated exceptional capabilities in speech-related tasks. Nevertheless, these models often struggle with non-verbal audio data, such as vocalizat…