voice (version 0.4.21)

read_rttm: Read RTTM files

Description

Read Rich Transcription Time Marked (RTTM) files in fromRttm directory.

Usage

read_rttm(fromRttm)

Value

A list containing data frames obtained from standard RTTM files. See 'Details'.

Arguments

fromRttm

A directory/folder containing RTTM files.

Details

The Rich Transcription Time Marked (RTTM) files are space-delimited text files containing one turn per line defined by NIST - National Institute of Standards and Technology. Each line containing ten fields:

type Type: segment type; should always by SPEAKER.

file File ID: file name; basename of the recording minus extension (e.g., rec1_a).

chnl Channel ID: channel (1-indexed) that turn is on; should always be 1.

tbeg Turn Onset -- onset of turn in seconds from beginning of recording.

tdur Turn Duration -- duration of turn in seconds.

ortho Orthography Field -- should always by <NA>.

stype Speaker Type -- should always be <NA>.

name Speaker Name -- name of speaker of turn; should be unique within scope of each file.

conf Confidence Score -- system confidence (probability) that information is correct; should always be <NA>.

slat Signal Lookahead Time -- should always be <NA>.

References

https://www.nist.gov/system/files/documents/itl/iad/mig/KWS15-evalplan-v05.pdf

See Also

voice::enrich_rttm

Examples

library(voice)

url0 <- 'https://raw.githubusercontent.com/filipezabala/voiceAudios/main/rttm/sherlock0.rttm'
download.file(url0, destfile = paste0(tempdir(), '/sherlock0.rttm'))
url1 <- 'https://raw.githubusercontent.com/filipezabala/voiceAudios/main/rttm/sherlock1.rttm'
download.file(url0, destfile = paste0(tempdir(), '/sherlock1.rttm'))

(rttm <- voice::read_rttm(tempdir()))
class(rttm)
lapply(rttm, class)