yaapt: Compute f0 using the algorithm named Yet Another Algorithm...

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

Compute f0 using the algorithm named Yet Another Algorithm for Pitch Tracking

Description

The Yet Another Algorithm for Pitch Tracking algorithm \insertCiteKasi.2002.10.1109/icassp.2002.5743729superassp that computes f0 using Normalized Cross Correlation (NCCF) and the work of Talkin \insertCitetalkin1995robustsuperassp in developing the RAPT algorithm.

Usage

yaapt(
  listOfFiles,
  beginTime = 0,
  endTime = 0,
  windowShift = 5,
  windowSize = 35,
  minF = 70,
  maxF = 200,
  tda_frame_length = 35,
  fft_length = 8192,
  bp_forder = 150,
  bp_low = 50,
  bp_high = 1500,
  nlfer_thresh1 = 0.75,
  nlfer_thresh2 = 0.1,
  shc_numharms = 3,
  shc_window = 40,
  shc_maxpeaks = 4,
  shc_pwidth = 50,
  shc_thresh1 = 5,
  shc_thresh2 = 1.25,
  f0_double = 150,
  f0_half = 150,
  dp5_k1 = 11,
  dec_factor = 1,
  nccf_thresh1 = 0.3,
  nccf_thresh2 = 0.9,
  nccf_maxcands = 3,
  nccf_pwidth = 5,
  merit_boost = 0.2,
  merit_pivot = 0.99,
  merit_extra = 0.4,
  median_value = 7,
  dp_w1 = 0.15,
  dp_w2 = 0.5,
  dp_w3 = 0.1,
  dp_w4 = 0.9,
  explicitExt = "yf0",
  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.
windowSize	length of each analysis frame (default: 35 ms)
minF	Candidate f0 frequencies below this frequency will not be considered.
maxF	Candidates above this frequency will be ignored.
tda_frame_length	The frame length employed in the time domain analysis (defaults to the same as windowSize 35 ms).
fft_length	FFT length (default: 8192 samples)
bp_forder	order of band-pass filter (default: 150)
bp_low	low frequency of filter passband (default: 50 Hz)
bp_high	high frequency of filter passband (default: 1500 Hz)
nlfer_thresh1	NLFER (Normalized Low Frequency Energy Ratio) boundary for voiced/unvoiced decisions (default: 0.75)
nlfer_thresh2	threshold for NLFER definitely unvoiced (default: 0.1)
shc_numharms	number of harmonics in SHC (Spectral Harmonics Correlation) calculation (default: 3)
shc_window	SHC window length (default: 40 Hz)
shc_maxpeaks	maximum number of SHC peaks to be found (default: 4)
shc_pwidth	window width in SHC peak picking (default: 50 Hz)
shc_thresh1	threshold 1 for SHC peak picking (default: 5)
shc_thresh2	threshold 2 for SHC peak picking (default: 1.25)
f0_double	pitch doubling decision threshold (default: 150 Hz)
f0_half	pitch halving decision threshold (default: 150 Hz)
dp5_k1	weight used in dynamic program (default: 11)
dec_factor	factor for signal resampling (default: 1)
nccf_thresh1	threshold for considering a peak in NCCF (Normalized Cross Correlation Function) (default: 0.3)
nccf_thresh2	threshold for terminating search in NCCF (default: 0.9)
nccf_maxcands	maximum number of candidates found (default: 3)
nccf_pwidth	window width in NCCF peak picking (default: 5)
merit_boost	boost merit (default. 0.20)
merit_pivot	merit assigned to unvoiced candidates in definitely unvoiced frames (default: 0.99)
merit_extra	merit assigned to extra candidates in reducing pitch doubling/halving errors (default: 0.4)
median_value	order of medial filter (default: 7)
dp_w1	DP (Dynamic Programming) weight factor for voiced-voiced transitions (default: 0.15)
dp_w2	DP weight factor for voiced-unvoiced or unvoiced-voiced transitions (default: 0.5)
dp_w3	DP weight factor of unvoiced-unvoiced transitions (default: 0.1)
dp_w4	Weight factor for local costs (default: 0.9)
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.

Details

The YAAPT algorithm processes the original acoustic signal and a non-linearly processed version of the signal to partially restore very weak f0 components. Intelligent peak picking to select multiple f0 candidates and assign merit factors; and, incorporation of highly robust pitch contours obtained from smoothed versions of low frequency portions of spectrograms. Dynamic programming is used to find the “best” pitch track among all the candidates, using both local and transition costs.

Value

An SSFF track object containing two tracks ("f0" and "voiced") which contains the computed pitch values, and a binary (0 or 1) indication of whether the frame was considered "voiced" (1) or not (0). The tracks are either returned (toFile == FALSE) or stored on disk.

References

\insertAllCited

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