DET (version 2.0.2)

speaker: Speaker Recognition System (Voxceleb verification test)

Description

For our experiments, we have used the Voxceleb database, which contains more than one hundred thousand utterances extracted from Youtube interview videos. The database includes training and test sets that can be used for speaker recognition system development and performance evaluation respectively. The testing protocol consists of a list of utterance pairs, with the corresponding target or nontarget, and the task is to detect whether the two utterances belong to the same speaker or to different ones.

Usage

data(speaker)

Format

An object of class "data.frame".

References

Nagraniy A, Chungy JS, Zisserman A (2017). Proceedings of the Annual Conference of the International Speech Communication Association, 950:2616<U+2013>2620 (Publication)

Examples

# NOT RUN {
data(speaker)
scoresLDA <-speaker$scoresLDA
scoresPLDA <-speaker$scoresPLDA
scoresLDAPLDA <- speaker$scoresLDAPLDA
responses <- data.frame(speaker$keys$V3)
predictors <- data.frame(
  n1 = as.numeric(scoresLDA),
  n2 = as.numeric(scoresPLDA),
  n3 = as.numeric(scoresLDAPLDA)
)
detcurve <- detc(responses,predictors, 
                 names = c("LDA+DC","PLDA","LDA+PLDA"),
                 positive = "target",
                 title = "Voxceleb verification test",
                 plotROC = TRUE)

# }