DOI: 10.3389/fcomp.2020.624488
One-Liner
Used an ERNIE trained on transcripts for classification; inclusion of pause encoding made results better.
Novelty
- Instead of just looking at actual speech content, look at pauses specific as a feature engineering task
- \(89.6\%\) on the ADReSS Challenge dataset
Notable Methods
![](/ox-hugo/2022-06-24_20-45-47_screenshot.png)
Applied FA with pause encoding with standard .cha
semantics (short pauses, medium pauses, long pauses). Shoved all of this into an ERNIE.
Assay for performance was LOO
Key Figs
Fig 1
![](/ox-hugo/2022-06-24_20-43-43_screenshot.png)
This figure motivates the point that subjects with AD says oh and um more often; which prompted Table 1
Table 1
![](/ox-hugo/2022-06-24_20-44-31_screenshot.png)
Subjects with AD says uh a lot more often; no significance level calculations but ok.
Figure 5
![](/ox-hugo/2022-06-24_20-55-10_screenshot.png)
This figure is the result of a LOO study on the proposed model and presumably others before. X axis is the validation accuracy in question, Y is the density by which the score in X appears in an \(N=35\) LOO measurement.
This figure tells us that either way the ERNIE model is better than state of the art; furthermore, transcripts with pause encoding did better and did it better more of the time; that’s where the 89.6% came from.
New Concepts
Notes
Glorious.
![](/ox-hugo/2022-06-24_20-41-41_screenshot.png)