voiceActivity: voiceActivity This function takes the Wave object and returns...

In akinori-ito/vadeR: Voice Activity Detection

voiceActivity This function takes the Wave object and returns an array of the voice activity.

Description

voiceActivity This function takes the Wave object and returns an array of the voice activity.

Usage

voiceActivity(x, simple = TRUE, minlen = 50, maxlen = 1000,
  nclust = 4, frameshift = 0.01)

Arguments

x	The input Wave object or a matrix obtained by melfcc()
minlen	Minimum duration of segment (number of frames)
maxlen	Maximum duration of segment (number of frames)
nclust	Number of clusters, one of which should be silent
frameshift	The frame shift (sec), 10ms by default

Value

A vector of logical with length of number of frames. If the frame is the voice frame, the content of the vector is TRUE, otherwise FALSE.

Examples

## Not run: 
library(tuneR)
x <- readWave("speech.wav")
act <- voiceActivity(x)

## End(Not run)

akinori-ito/vadeR documentation built on Oct. 7, 2022, 2:37 p.m.