mindspore.dataset.audio.Spectrogram

class mindspore.dataset.audio.Spectrogram(n_fft=400, win_length=None, hop_length=None, pad=0, window=WindowType.HANN, power=2.0, normalized=False, center=True, pad_mode=BorderType.REFLECT, onesided=True)[source]

Create a spectrogram from an audio signal.

Parameters
  • n_fft (int, optional) – Size of FFT, creates n_fft // 2 + 1 bins. Default: 400.

  • win_length (int, optional) – Window size. Default: None, will use n_fft .

  • hop_length (int, optional) – Length of hop between STFT windows. Default: None, will use win_length // 2 .

  • pad (int, optional) – Two sided padding of signal. Default: 0.

  • window (WindowType, optional) – Window function that is applied/multiplied to each frame/window, can be WindowType.BARTLETT, WindowType.BLACKMAN, WindowType.HAMMING, WindowType.HANN or WindowType.KAISER. Currently, Kaiser window is not supported on macOS. Default: WindowType.HANN.

  • power (float, optional) – Exponent for the magnitude spectrogram, must be non negative, e.g., 1 for energy, 2 for power, etc. Default: 2.0.

  • normalized (bool, optional) – Whether to normalize by magnitude after stft. Default: False.

  • center (bool, optional) – Whether to pad waveform on both sides. Default: True.

  • pad_mode (BorderType, optional) – Controls the padding method used when center is True, can be BorderType.REFLECT, BorderType.CONSTANT, BorderType.EDGE or BorderType.SYMMETRIC. Default: BorderType.REFLECT.

  • onesided (bool, optional) – Controls whether to return half of results to avoid redundancy. Default: True.

Raises
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, 10, 20])  # 5 samples
>>> numpy_slices_dataset = ds.NumpySlicesDataset(data=waveform, column_names=["audio"])
>>> transforms = [audio.Spectrogram()]
>>> 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
(10, 201, 1) float64
>>>
>>> # Use the transform in eager mode
>>> waveform = np.random.random([10, 20])  # 1 sample
>>> output = audio.Spectrogram()(waveform)
>>> print(output.shape, output.dtype)
(10, 201, 1) float64
Tutorial Examples: