torch_pitch: Pitch tracking using the torch pitch tracker

In humlab-speech/superassp: A speech signal processing using various framworks using a wrassp-like interface

Pitch tracking using the torch pitch tracker

Description

This function estimates pitch by normalized cross-correlation function (NCCF) and median smoothing, as implemented in the torchaudio \insertCiteyang2021torchaudiosuperassp library. The exact algorithm is undisclosed by the implementing library but approach likely builds on earlier implementations that use NCCFs \insertCitetalkin1995robust,Kasi.2002.10.1109/icassp.2002.5743729superassp including the RAPT algorithm.

Usage

torch_pitch(
  listOfFiles,
  beginTime = 0,
  endTime = 0,
  windowShift = 10,
  windowSize = 30,
  minF = 70,
  maxF = 200,
  explicitExt = "tpi",
  outputDirectory = NULL,
  toFile = TRUE
)

Arguments

listOfFiles	A vector of file paths to wav files.
beginTime	The start time of the section of the sound file that should be processed.
endTime	The end time of the section of the sound file that should be processed.
windowShift	The measurement interval (frame duration), in seconds.
minF	Candidate f0 frequencies below this frequency will not be considered.
maxF	Candidates above this frequency will be ignored.
explicitExt	the file extension that should be used.
outputDirectory	set an explicit directory for where the signal file will be written. If not defined, the file will be written to the same directory as the sound file.
toFile	write the output to a file? The file will be written in outputDirectory, if defined, or in the same directory as the soundfile.

Value

An SSFF track object containing two tracks (f0 and pitch) that are either returned (toFile == FALSE) or stored on disk.

References

\insertAllCited

See Also

rapt

humlab-speech/superassp documentation built on May 8, 2024, 2:27 p.m.