Tackling Cognitive Impairment Detection from Speech: A submission to the PROCESS Challenge
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915086758576128 |
|---|---|
| author | Botelho, Catarina Gimeno-Gómez, David Teixeira, Francisco Mendonça, John Pereira, Patrícia Nunes, Diogo A. P. Rolland, Thomas Pompili, Anna Solera-Ureña, Rubén Ponte, Maria de Matos, David Martins Martínez-Hinarejos, Carlos-D. Trancoso, Isabel Abad, Alberto |
| author_facet | Botelho, Catarina Gimeno-Gómez, David Teixeira, Francisco Mendonça, John Pereira, Patrícia Nunes, Diogo A. P. Rolland, Thomas Pompili, Anna Solera-Ureña, Rubén Ponte, Maria de Matos, David Martins Martínez-Hinarejos, Carlos-D. Trancoso, Isabel Abad, Alberto |
| contents | This work describes our group's submission to the PROCESS Challenge 2024, with the goal of assessing cognitive decline through spontaneous speech, using three guided clinical tasks. This joint effort followed a holistic approach, encompassing both knowledge-based acoustic and text-based feature sets, as well as LLM-based macrolinguistic descriptors, pause-based acoustic biomarkers, and multiple neural representations (e.g., LongFormer, ECAPA-TDNN, and Trillson embeddings). Combining these feature sets with different classifiers resulted in a large pool of models, from which we selected those that provided the best balance between train, development, and individual class performance. Our results show that our best performing systems correspond to combinations of models that are complementary to each other, relying on acoustic and textual information from all three clinical tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00145 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Tackling Cognitive Impairment Detection from Speech: A submission to the PROCESS Challenge Botelho, Catarina Gimeno-Gómez, David Teixeira, Francisco Mendonça, John Pereira, Patrícia Nunes, Diogo A. P. Rolland, Thomas Pompili, Anna Solera-Ureña, Rubén Ponte, Maria de Matos, David Martins Martínez-Hinarejos, Carlos-D. Trancoso, Isabel Abad, Alberto Audio and Speech Processing Sound This work describes our group's submission to the PROCESS Challenge 2024, with the goal of assessing cognitive decline through spontaneous speech, using three guided clinical tasks. This joint effort followed a holistic approach, encompassing both knowledge-based acoustic and text-based feature sets, as well as LLM-based macrolinguistic descriptors, pause-based acoustic biomarkers, and multiple neural representations (e.g., LongFormer, ECAPA-TDNN, and Trillson embeddings). Combining these feature sets with different classifiers resulted in a large pool of models, from which we selected those that provided the best balance between train, development, and individual class performance. Our results show that our best performing systems correspond to combinations of models that are complementary to each other, relying on acoustic and textual information from all three clinical tasks. |
| title | Tackling Cognitive Impairment Detection from Speech: A submission to the PROCESS Challenge |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2501.00145 |