To BERT or not to BERT: comparing speech and language-based approaches for Alzheimer's disease detection
Research related to automatically detecting Alzheimer's disease (AD) is important, given the
high prevalence of AD and the high cost of traditional methods. Since AD significantly affects …
high prevalence of AD and the high cost of traditional methods. Since AD significantly affects …
Comparing pre-trained and feature-based models for prediction of Alzheimer's disease based on speech
Introduction: Research related to the automatic detection of Alzheimer's disease (AD) is
important, given the high prevalence of AD and the high cost of traditional diagnostic …
important, given the high prevalence of AD and the high cost of traditional diagnostic …
Comparing acoustic-based approaches for Alzheimer's disease detection
A Balagopalan, J Novikova - arXiv preprint arXiv:2106.01555, 2021 - arxiv.org
Robust strategies for Alzheimer's disease (AD) detection are important, given the high
prevalence of AD. In this paper, we study the performance and generalizability of three …
prevalence of AD. In this paper, we study the performance and generalizability of three …
Situated Natural Language Explanations
Natural language is among the most accessible tools for explaining decisions to humans,
and large pretrained language models (PLMs) have demonstrated impressive abilities to …
and large pretrained language models (PLMs) have demonstrated impressive abilities to …
Zero-Shot Multi-Lingual Speaker Verification in Clinical Trials
A Akram, M Stanojevic, M Ehghaghi… - arXiv preprint arXiv …, 2024 - arxiv.org
Due to the substantial number of clinicians, patients, and data collection environments
involved in clinical trials, gathering data of superior quality poses a significant challenge. In …
involved in clinical trials, gathering data of superior quality poses a significant challenge. In …
Deconfounding age effects with fair representation learning when assessing dementia
One of the most prevalent symptoms among the elderly population, dementia, can be
detected by classifiers trained on linguistic features extracted from narrative transcripts …
detected by classifiers trained on linguistic features extracted from narrative transcripts …
A Computational Basis for Consensus-Aware Technologies
N Gürkan - 2024 - search.proquest.com
This dissertation studies the advancement of consensus-aware technologies in the context
of collective decision-making, focusing on the integration of these technologies into …
of collective decision-making, focusing on the integration of these technologies into …
Impact of Environmental Noise on Alzheimer's Disease Detection from Speech: Should You Let a Baby Cry?
J Novikova - arXiv preprint arXiv:2203.17110, 2022 - arxiv.org
Research related to automatically detecting Alzheimer's disease (AD) is important, given the
high prevalence of AD and the high cost of traditional methods. Since AD significantly affects …
high prevalence of AD and the high cost of traditional methods. Since AD significantly affects …
[PDF][PDF] On Speech Datasets in Machine Learning for Healthcare
J Novikova, A Balagopalan - 2020 - aphasia.talkbank.org
Multi-language speech datasets are scarce and often have small sample sizes in the
medical domain. We address this problem by employing the cross-linguistic transfer …
medical domain. We address this problem by employing the cross-linguistic transfer …
Variations on the Chebyshev-Lagrange Activation Function
Y Li, F Rudzicz, J Novikova - arXiv preprint arXiv:1906.10064, 2019 - arxiv.org
We seek to improve the data efficiency of neural networks and present novel
implementations of parameterized piece-wise polynomial activation functions. The …
implementations of parameterized piece-wise polynomial activation functions. The …