Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2022 Oct 3;13:5815. doi: 10.1038/s41467-022-33457-9

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2022

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Fig. 4 — a T-distributed stochastic neighbor embedding (t-SNE) of 100 words, visualizing the result of validation 1 in Fig. 3b. All 100 words are allocated in points of different colors. The denser the cluster of same-colored points is plotted, the more the model classifies them as similar data. b t-SNE of the most confused 10 words out of 100 words. c Two pairs of normalized waveforms of words exhibiting similar facial movement during pronunciation (FAMILY/FAMILIES and INCREASE/DEGREES). d Relevance-CAM (R-CAM) that explains our model by highlighting which region of the entire waveform is dominant to classify each word, demonstrating that the model focuses on characteristic signal parts where the variance of the resistance is large.