Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: La Quatra, Moreno, Turco, Maria Francesca, Svendsen, Torbjørn, Salvi, Giampiero, Orozco-Arroyave, Juan Rafael, Siniscalchi, Sabato Marco
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914151652130816
author La Quatra, Moreno
Turco, Maria Francesca
Svendsen, Torbjørn
Salvi, Giampiero
Orozco-Arroyave, Juan Rafael
Siniscalchi, Sabato Marco
author_facet La Quatra, Moreno
Turco, Maria Francesca
Svendsen, Torbjørn
Salvi, Giampiero
Orozco-Arroyave, Juan Rafael
Siniscalchi, Sabato Marco
contents This work is concerned with devising a robust Parkinson's (PD) disease detector from speech in real-world operating conditions using (i) foundational models, and (ii) speech enhancement (SE) methods. To this end, we first fine-tune several foundational-based models on the standard PC-GITA (s-PC-GITA) clean data. Our results demonstrate superior performance to previously proposed models. Second, we assess the generalization capability of the PD models on the extended PC-GITA (e-PC-GITA) recordings, collected in real-world operative conditions, and observe a severe drop in performance moving from ideal to real-world conditions. Third, we align training and testing conditions applaying off-the-shelf SE techniques on e-PC-GITA, and a significant boost in performance is observed only for the foundational-based models. Finally, combining the two best foundational-based models trained on s-PC-GITA, namely WavLM Base and Hubert Base, yielded top performance on the enhanced e-PC-GITA.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16128
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions
La Quatra, Moreno
Turco, Maria Francesca
Svendsen, Torbjørn
Salvi, Giampiero
Orozco-Arroyave, Juan Rafael
Siniscalchi, Sabato Marco
Audio and Speech Processing
This work is concerned with devising a robust Parkinson's (PD) disease detector from speech in real-world operating conditions using (i) foundational models, and (ii) speech enhancement (SE) methods. To this end, we first fine-tune several foundational-based models on the standard PC-GITA (s-PC-GITA) clean data. Our results demonstrate superior performance to previously proposed models. Second, we assess the generalization capability of the PD models on the extended PC-GITA (e-PC-GITA) recordings, collected in real-world operative conditions, and observe a severe drop in performance moving from ideal to real-world conditions. Third, we align training and testing conditions applaying off-the-shelf SE techniques on e-PC-GITA, and a significant boost in performance is observed only for the foundational-based models. Finally, combining the two best foundational-based models trained on s-PC-GITA, namely WavLM Base and Hubert Base, yielded top performance on the enhanced e-PC-GITA.
title Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions
topic Audio and Speech Processing
url https://arxiv.org/abs/2406.16128