vocalpy.feature.sat

vocalpy.feature.sat(sound: Sound, n_fft=400, hop_length=40, freq_range=0.5, min_freq: float = 380.0, amp_baseline: float = 70.0, max_F0: float = 1830.0, fmax_yin: float = 8000.0, trough_threshold: float = 0.1) → Features

Extract all features used to compute similarity with the Sound Analysis Toolbox for Matlab (SAT).

Parameters:

soundSound

A Sound. Multi-channel sounds are supported.

n_fftint

FFT window size.

hop_lengthint

Number of audio samples between adjacent STFT columns.

freq_rangefloat

Range of frequencies to use, given as a value between zero and one. Default is 0.5, which means “Use the first half of the frequencies, from zero to \(f_s/4\) (half the Nyquist frequency)”.

min_freqfloat

Minimum frequency to consider when extracting features.

amp_baselinefloat

The baseline value added, in decibels, to the amplitude feature. The default is 70.0 dB, the value used by SAT and SAP.

max_F0float

Maximum frequency to consider, that becomes the lowest quefrency used when computing goodness of pitch.

fmax_yinfloat

Maximum frequency in Hertz when computing pitch with YIN algorithm. Default is 8000.

trough_threshold: float

Absolute threshold for peak estimation. A float greater than 0. Used by pitch().

Returns:

featuresvocalpy.Features

vocalpy.Features instance with data attribute that is an xarray.Dataset, where the data variables are the features, and the coordinate is the time for each time bin.