Useful Blunders: Can Automated Speech Recognition Errors Improve Downstream Dementia Classification?

no code implementations • 10 Jan 2024 • Changye Li, Weizhe Xu, Trevor Cohen, Serguei Pakhomov

\textbf{Results}: Imperfect ASR-generated transcripts surprisingly outperformed manual transcription for distinguishing between individuals with AD and those without in the ``Cookie Theft'' task.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

TRESTLE: Toolkit for Reproducible Execution of Speech, Text and Language Experiments

1 code implementation • 14 Feb 2023 • Changye Li, Weizhe Xu, Trevor Cohen, Martin Michalowski, Serguei Pakhomov

The evidence is growing that machine and deep learning methods can learn the subtle differences between the language produced by people with various forms of cognitive impairment such as dementia and cognitively healthy individuals.

The Far Side of Failure: Investigating the Impact of Speech Recognition Errors on Subsequent Dementia Classification

1 code implementation • 11 Nov 2022 • Changye Li, Trevor Cohen, Serguei Pakhomov

Linguistic anomalies detectable in spontaneous speech have shown promise for various clinical applications including screening for dementia and other forms of cognitive impairment.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Models

2 code implementations • ACL 2022 • Changye Li, David Knopman, Weizhe Xu, Trevor Cohen, Serguei Pakhomov

Deep learning (DL) techniques involving fine-tuning large numbers of model parameters have delivered impressive performance on the task of discriminating between language produced by cognitively healthy individuals, and those with Alzheimer's disease (AD).