Compute Mel-filterbank energy features from audio

This function computes Mel-filterbank energy features from audio signals. Clone of get_mel.

get_fbs(
  chopped_dir,
  sample_rate = 16000,
  winlen = 0.005,
  steptime = 0.01,
  fft = 512,
  nfilt = 21,
  dither = FALSE
)

Arguments

chopped_dir

Directory of the individual sound files. Typically created with get_word_sound_files.

sample_rate

Sample rate of your wav files. Default is 16000.

winlen

The length of the analysis window in seconds. Default is 0.005.

steptime

The step between successive windows in seconds. Default is 0.01.

fft

The FFT size. Default is 512.

nfilt

The number of filters in the filterbank. Default is 21.

dither

Add dither to MEL features. Defaults to FALSE.

Value

A list object.

References

Ligges, U., Krey, S., Mersmann, O., & Schnackenberg, S. (2023). tuneR: Analysis of Music and Speech. Retrieved from https://CRAN.R-project.org/package=tuneR

Signal developers. (2023). signal: Signal processing. Retrieved from https://r-forge.r-project.org/projects/signal/

Author

Dominic Schmitz

Examples

if (FALSE) fbs_data <- get_fbs(chopped_dir = "/chopped")