Summary of Connected Speech-based Cognitive Assessment in Chinese and English, by Saturnino Luz et al.
Connected Speech-Based Cognitive Assessment in Chinese and English
by Saturnino Luz, Sofia De La Fuente Garcia, Fasih Haider, Davida Fromm, Brian MacWhinney, Alyssa Lanzi, Ya-Ning Chang, Chia-Ju Chou, Yi-Chien Liu
First submitted to arxiv on: 11 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a novel benchmark dataset and prediction tasks to assess cognitive function through analysis of connected speech. A unique aspect is the inclusion of speakers from Mandarin Chinese and English, with varying levels of cognitive impairment, as well as individuals with normal cognition. The prediction tasks focus on mild cognitive impairment diagnosis and cognitive test score prediction. To ensure model training fairness, the dataset was carefully matched by age and sex using propensity score analysis. Baseline models employing language-agnostic features were developed for diagnosis (59.2% unweighted average recall) and score prediction (2.89 root mean squared error). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way to test how well computer programs can tell if someone has cognitive problems just by listening to them talk. It uses speech from people who speak Mandarin Chinese or English, some with brain impairments and others without. The goal is to make it work for both languages. Some simple models were made to see how well they could do this job. |
Keywords
» Artificial intelligence » Recall
