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

. 2023 Jun 24;13:10270. doi: 10.1038/s41598-023-36701-4

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

© The Author(s) 2023

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 licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence 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 licence, visit http://creativecommons.org/licenses/by/4.0/.

PMC Copyright notice

Task design, diarization methods, and feature extraction. Participants took part in (A) a conversation with a study partner, and (B) a Describe the Picture (DtP) task. (C) Conversations were automatically diarized into a hypothesised number of unknown speakers. (D) DtP audio was manually segmented to extract participant speech only. (E,F) The audio for each hypothesised speaker, and for the participant’s speech, were converted into fixed 192 dimensional embeddings. (G) The distances between the speaker embeddings and the participant’s embedding were measured using the cosine distance. (H) Speakers who’s distance was less than a predefined threshold (0.75: Spk1/Spk3 in this example) were assigned to be the participant. (I) The duration of each utterance was measured, and their basic statistics were calculated.