Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from Speech
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911260132507648 |
|---|---|
| author | La Quatra, Moreno Orozco-Arroyave, Juan Rafael Siniscalchi, Marco Sabato |
| author_facet | La Quatra, Moreno Orozco-Arroyave, Juan Rafael Siniscalchi, Marco Sabato |
| contents | This work aims to tackle the Parkinson's disease (PD) detection problem from the speech signal in a bilingual setting by proposing an ad-hoc dual-head deep neural architecture for type-based binary classification. One head is specialized for diadochokinetic patterns. The other head looks for natural speech patterns present in continuous spoken utterances. Only one of the two heads is operative accordingly to the nature of the input. Speech representations are extracted from self-supervised learning (SSL) models and wavelet transforms. Adaptive layers, convolutional bottlenecks, and contrastive learning are exploited to reduce variations across languages. Our solution is assessed against two distinct datasets, EWA-DB, and PC-GITA, which cover Slovak and Spanish languages, respectively. Results indicate that conventional models trained on a single language dataset struggle with cross-linguistic generalization, and naive combinations of datasets are suboptimal. In contrast, our model improves generalization on both languages, simultaneously. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10301 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from Speech La Quatra, Moreno Orozco-Arroyave, Juan Rafael Siniscalchi, Marco Sabato Audio and Speech Processing Artificial Intelligence This work aims to tackle the Parkinson's disease (PD) detection problem from the speech signal in a bilingual setting by proposing an ad-hoc dual-head deep neural architecture for type-based binary classification. One head is specialized for diadochokinetic patterns. The other head looks for natural speech patterns present in continuous spoken utterances. Only one of the two heads is operative accordingly to the nature of the input. Speech representations are extracted from self-supervised learning (SSL) models and wavelet transforms. Adaptive layers, convolutional bottlenecks, and contrastive learning are exploited to reduce variations across languages. Our solution is assessed against two distinct datasets, EWA-DB, and PC-GITA, which cover Slovak and Spanish languages, respectively. Results indicate that conventional models trained on a single language dataset struggle with cross-linguistic generalization, and naive combinations of datasets are suboptimal. In contrast, our model improves generalization on both languages, simultaneously. |
| title | Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from Speech |
| topic | Audio and Speech Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2503.10301 |