Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
vocaldia
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Commits
Issue Boards
Open sidebar
Saturnino Luz
vocaldia
Commits
7d960d0f
Commit
7d960d0f
authored
May 08, 2020
by
S Luz
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Now really added it.
parent
9741e68c
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
67 additions
and
0 deletions
+67
-0
README.md
README.md
+67
-0
No files found.
README.md
0 → 100644
View file @
7d960d0f
# vocaldia
<!-- badges: start -->
<!-- badges: end -->
This package contains functions that create and manipulate vocalisation
diagrams. Vocalisation diagrams date back to early work in psychiatry
(Jaffe and Feldstein, 1970) and social psychology (Dabbs and Ruback,
1987) but have only recently been employed as a data representation
method for machine learning (Luz, 2013; Luz and Kane, 2009).
This provides a number of functions for generating vocalisation
diagrams (vocaldias) from data frames containing, minimally, a column
for start time of a vocalisation event (speech, silence, group-talk
etc), a column for end time, and a column for the event identifier. It
also contains some basic functions for reading and processing files
from DementiaBank (.cha transcripts and audio files).
Functions
`getSampledVocalMatrix`
and
`getTurnTakingProbMatrix`
generate alternative versions of adjacency matrices for
vocaldias.
`staticMatrix`
generates steady state diagrams from a
vocaldia.
`printARFFfile`
generates a 'flat' representation of
vocaldias for classifier training and evaluation.
## Installation
You can install the released version of vocaldia from
[
CRAN
](
https://CRAN.R-project.org
)
with:
```
r
install.packages
(
"vocaldia"
)
```
## Example
The following examples illustrate the use of vocaldia to create and
visualise vocalisation graphs and their properties.
``` r
library(vocaldia)
## load some data
data(vocdia)
## select a dialogue
x <- subset(atddia, id=='Abbott_Maddock_01')
## show a probability matrix
getTurnTakingProbMatrix(x)
## if you have igraph installed, visualise a vocal matrix
require('igraph')
subset(atddia, id=='Abbott_Maddock_01') %>%
getSampledVocalMatrix(individual=TRUE, nodecolumn='speaker')
%>% igraph.vocaldia %>% plot
## plot steady state of the Markov diagram
plot(staticMatrix(vocmatrix$ttarray, digits=4, history=TRUE))
```
See the following publication for further examples of use of this
package:
Luz S, De La Fuente Garcia S, Albert P. A Method for Analysis of
Patient Speech in Dialogue for Dementia Detection. In Resources and
ProcessIng of linguistic, para-linguistic and extra-linguistic Data
from people with various forms of cognitive impairment. Paris, France:
ELRA. 2018. p. 35-42 (https://arxiv.org/abs/1811.09919)
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment