mindspore.dataset.audio.GriffinLim

class mindspore.dataset.audio.GriffinLim(n_fft=400, n_iter=32, win_length=None, hop_length=None, window_type=WindowType.HANN, power=2.0, momentum=0.99, length=None, rand_init=True)[source]

Compute waveform from a linear scale magnitude spectrogram using the Griffin-Lim transformation.

About Griffin-Lim please refer to A fast Griffin-Lim algorithm and Signal estimation from modified short-time Fourier transform .

Parameters

n_fft (int, optional) – Size of FFT. Default: 400.
n_iter (int, optional) – Number of iteration for phase recovery. Default: 32.
win_length (int, optional) – Window size for Griffin-Lim. Default: None, will be set to n_fft .
hop_length (int, optional) – Length of hop between STFT windows. Default: None, will be set to win_length // 2 .
window_type (WindowType, optional) – Window type for Griffin-Lim, which can be WindowType.BARTLETT, WindowType.BLACKMAN, WindowType.HAMMING, WindowType.HANN or WindowType.KAISER. Default: WindowType.HANN. Currently kaiser window is not supported on macOS.
power (float, optional) – Exponent for the magnitude spectrogram. Default: 2.0.
momentum (float, optional) – The momentum for fast Griffin-Lim. Default: 0.99.
length (int, optional) – Length of the expected output waveform. Default: None, will be set to the value of last dimension of the stft matrix.
rand_init (bool, optional) – Flag for random phase initialization or all-zero phase initialization. Default: True.

Raises

TypeError – If n_fft is not of type int.
ValueError – If n_fft is not positive.
TypeError – If n_iter is not of type int.
ValueError – If n_iter is not positive.
TypeError – If win_length is not of type int.
ValueError – If win_length is a negative number.
TypeError – If hop_length is not of type int.
ValueError – If hop_length is a negative number.
TypeError – If window_type is not of type mindspore.dataset.audio.WindowType .
TypeError – If power is not of type float.
ValueError – If power is not positive.
TypeError – If momentum is not of type float.
ValueError – If momentum is a negative number.
TypeError – If length is not of type int.
ValueError – If length is a negative number.
TypeError – If rand_init is not of type bool.
RuntimeError – If n_fft is not less than length .
RuntimeError – If win_length is not less than n_fft .

Supported Platforms:: CPU

Examples

>>> import numpy as np
>>> import mindspore.dataset as ds
>>> import mindspore.dataset.audio as audio
>>>
>>> # Use the transform in dataset pipeline mode
>>> waveform = np.random.random([5, 201, 6])  # 5 samples
>>> numpy_slices_dataset = ds.NumpySlicesDataset(data=waveform, column_names=["audio"])
>>> transforms = [audio.GriffinLim(n_fft=400)]
>>> numpy_slices_dataset = numpy_slices_dataset.map(operations=transforms, input_columns=["audio"])
>>> for item in numpy_slices_dataset.create_dict_iterator(num_epochs=1, output_numpy=True):
...     print(item["audio"].shape, item["audio"].dtype)
...     break
(1000,) float64
>>>
>>> # Use the transform in eager mode
>>> waveform = np.random.random([201, 6])  # 1 sample
>>> output = audio.GriffinLim(n_fft=400)(waveform)
>>> print(output.shape, output.dtype)
(1000,) float64

Tutorial Examples:

Illustration of audio transforms