Voice Disorder Analysis: a Transformer-based Approach

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Koudounas, Alkis, Ciravegna, Gabriele, Fantini, Marco, Succo, Giovanni, Crosetti, Erika, Cerquitelli, Tania, Baralis, Elena
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912028050849792
author Koudounas, Alkis
Ciravegna, Gabriele
Fantini, Marco
Succo, Giovanni
Crosetti, Erika
Cerquitelli, Tania
Baralis, Elena
author_facet Koudounas, Alkis
Ciravegna, Gabriele
Fantini, Marco
Succo, Giovanni
Crosetti, Erika
Cerquitelli, Tania
Baralis, Elena
contents Voice disorders are pathologies significantly affecting patient quality of life. However, non-invasive automated diagnosis of these pathologies is still under-explored, due to both a shortage of pathological voice data, and diversity of the recording types used for the diagnosis. This paper proposes a novel solution that adopts transformers directly working on raw voice signals and addresses data shortage through synthetic data generation and data augmentation. Further, we consider many recording types at the same time, such as sentence reading and sustained vowel emission, by employing a Mixture of Expert ensemble to align the predictions on different data types. The experimental results, obtained on both public and private datasets, show the effectiveness of our solution in the disorder detection and classification tasks and largely improve over existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14693
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Voice Disorder Analysis: a Transformer-based Approach
Koudounas, Alkis
Ciravegna, Gabriele
Fantini, Marco
Succo, Giovanni
Crosetti, Erika
Cerquitelli, Tania
Baralis, Elena
Audio and Speech Processing
Machine Learning
Voice disorders are pathologies significantly affecting patient quality of life. However, non-invasive automated diagnosis of these pathologies is still under-explored, due to both a shortage of pathological voice data, and diversity of the recording types used for the diagnosis. This paper proposes a novel solution that adopts transformers directly working on raw voice signals and addresses data shortage through synthetic data generation and data augmentation. Further, we consider many recording types at the same time, such as sentence reading and sustained vowel emission, by employing a Mixture of Expert ensemble to align the predictions on different data types. The experimental results, obtained on both public and private datasets, show the effectiveness of our solution in the disorder detection and classification tasks and largely improve over existing approaches.
title Voice Disorder Analysis: a Transformer-based Approach
topic Audio and Speech Processing
Machine Learning
url https://arxiv.org/abs/2406.14693