atddia: A sample Medical Team Meeting dialogue encoded as a vocaldia

Description Usage Format Source

Description

A dataset containing 38 dialogues (17 control patients, and 21 AD patients) and 7869 vocalisation events.

Usage

1

Format

A data frame with 7869 rows and 7 variables:

id

The dialogue indentifier

begin

The start time of a speech turn or silence interval

end

The end time of a speech turn or silence interval

speaker

An identifier for the speaker of the turn, or Floor for silence.

role

The speaker's role (patient, interviewer, other, or Floor

trans

The transcription of the turn (blanked out for anonymity)

dx

The diagnosis (ad or nonad

Source

This dataset was generated from the Carolina Conversations Collection, and used in the work described in De La Fuente, Albert and Luz: "Detecting cognitive decline through dialogue processing", 2017. For the full data set, please contact the Medical University of South Carolina (MUSC) http://carolinaconversations.musc.edu/


vocaldia documentation built on July 2, 2020, 2 a.m.