Publications by authors named "J R Liss"
Speech foundation models are remarkably successful in various consumer applications, prompting their extension to clinical use-cases. This is challenged by small clinical datasets, which precludes effective fine-tuning. We tested the efficacy of two models to classify participants by segmental (Wav2Vec2.
View Article and Find Full Text PDFArticle Synopsis
- - This study explores the relationship between mild cognitive impairment (MCI), a potential precursor to Alzheimer's disease, and articulatory precision in speech by introducing a new measure called the phoneme log-likelihood ratio (PLLR).
- - Researchers analyzed speech recordings from various groups, including cognitively unimpaired individuals and those with MCI or dementia, and found that MCI and dementia participants displayed reduced speech fluency and pace.
- - The PLLR demonstrated strong effectiveness in distinguishing between cognitively unimpaired participants and those with cognitive decline, highlighting its potential as a sensitive tool for detecting early changes in speech related to cognitive health.
Source monitoring involves attributing previous experiences (e.g., studied words as items) to their origins (e.
View Article and Find Full Text PDFArticle Synopsis
- This study examines kidney retransplantation (re-KT) outcomes specifically comparing HIV-positive (HIV+) and HIV-negative (HIV-) patients from 2014 to 2022.
- The research shows that HIV+ recipients face higher risks of graft loss due to factors like being more likely to be Black, experiencing delayed graft function, and having significant HLA mismatches.
- The findings indicate a need for better organ matching and strategies to improve re-KT success in HIV+ patients, as they exhibited significantly lower graft survival rates overall.
This perspective article explores the challenges and potential of using speech as a biomarker in clinical settings, particularly when constrained by the small clinical datasets typically available in such contexts. We contend that by integrating insights from speech science and clinical research, we can reduce sample complexity in clinical speech AI models with the potential to decrease timelines to translation. Most existing models are based on high-dimensional feature representations trained with limited sample sizes and often do not leverage insights from speech science and clinical research.
View Article and Find Full Text PDF