functional_detect_pitch_frequency {torchaudio} | R Documentation |
Detect Pitch Frequency (functional)
Description
It is implemented using normalized cross-correlation function and median smoothing.
Usage
functional_detect_pitch_frequency(
waveform,
sample_rate,
frame_time = 10^(-2),
win_length = 30,
freq_low = 85,
freq_high = 3400
)
Arguments
waveform |
(Tensor): Tensor of audio of dimension (..., freq, time) |
sample_rate |
(int): The sample rate of the waveform (Hz) |
frame_time |
(float, optional): Duration of a frame (Default: |
win_length |
(int, optional): The window length for median smoothing (in number of frames) (Default: |
freq_low |
(int, optional): Lowest frequency that can be detected (Hz) (Default: |
freq_high |
(int, optional): Highest frequency that can be detected (Hz) (Default: |
Value
Tensor: Tensor of freq of dimension (..., frame)
[Package torchaudio version 0.3.1 Index]