Alzheimer’s Disease Detection from Spontaneous Speech Through Combining Linguistic Complexity and (Dis)Fluency Features with Pretrained Language Models
| Authors |
|
|---|---|
| Publication date | 2021 |
| Journal | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
| Event | Interspeech 2021 |
| Volume | Issue number | 22 |
| Pages (from-to) | 3805-3809 |
| Organisations |
|
| Abstract | In this paper, we combined linguistic complexity and (dis)fluency features with pretrained language models for the task of Alzheimer’s disease detection of the 2021 ADReSSo (Alzheimer’s Dementia Recognition through Spontaneous Speech) challenge. An accuracy of 83.1% was achieved on the test set, which amounts to an improvement of 4.23% over the baseline model. Our best-performing model that integrated component models using a stacking ensemble technique performed equally well on cross-validation and test data, indicating that it is robust against overfitting. |
| Document type | Article |
| Note | 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH 2021) : Brno, Czech Republic, 30 August-3 September 2021. - In print proceedings pp. 4226-4230. |
| Language | English |
| Published at | https://doi.org/10.21437/Interspeech.2021-1415 |
| Other links | https://www.proceedings.com/60667.html |
| Downloads |
qiao21_interspeech
(Final published version)
|
| Permalink to this page | |