Description Usage Arguments Value Examples
View source: R/evaluate_roles.R
evaluate speaker roles
1 2 3 4 |
test |
character, path to file with annotations in DiViMe (.rttm) format |
reference |
character, path to reference file with annotations in DiViMe (.rttm) format |
resolution |
numeric, the time increment in seconds, by default 1 |
duration |
numeric, optional info about the duration of the audio. At its default |
summarize |
logical (default is |
tiers |
a named list that controls which labels/speakers from reference and test annotation are used. The name of each element needs to correspond to the speakers/'tiers' in the test file, e.g. |
test_ignore, ref_ignore |
character, the annotation values to be ignored. At its default |
allspeech |
logical, should the speech detection be taken from all tiers, i.e. even those that were ignored by setting |
a data.frame (for summarize = TRUE
) or matrix (for summarize = FALSE
)
1 2 3 4 5 6 7 | reference <- read_elan(system.file("spanish.eaf", package = "avutils"))
test <- read_rttm(system.file("yunitator_old_spanish.rttm", package = "avutils"))
evaluate_roles(reference = reference, test = test, duration = 180, resolution = 10)
# use for pure speech detection
# not quite working yet...
# test <- read_rttm(system.file("tocomboSad_spanish.rttm", package = "avutils"))
# evaluate_roles(reference = reference, test = test, duration = 180, resolution = 10)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.