mindspore.dataset.audio.transforms.BandBiquad

class mindspore.dataset.audio.transforms.BandBiquad(sample_rate, central_freq, Q=0.707, noise=False)[source]

Design two-pole band filter for audio waveform of dimension of (…, time).

Parameters

sample_rate (int) – Sampling rate of the waveform, e.g. 44100 (Hz), the value can’t be zero.
central_freq (float) – Central frequency (in Hz).
Q (float, optional) – Quality factor, https://en.wikipedia.org/wiki/Q_factor, range: (0, 1] (default=0.707).
noise (bool, optional) – If True, uses the alternate mode for un-pitched audio (e.g. percussion). If False, uses mode oriented to pitched audio, i.e. voice, singing, or instrumental music (default=False).

Examples

>>> import numpy as np
>>>
>>> waveform = np.array([[2.716064453125e-03, 6.34765625e-03], [9.246826171875e-03, 1.0894775390625e-02]])
>>> numpy_slices_dataset = ds.NumpySlicesDataset(data=waveform, column_names=["audio"])
>>> transforms = [audio.BandBiquad(44100, 200.0)]
>>> numpy_slices_dataset = numpy_slices_dataset.map(operations=transforms, input_columns=["audio"])