ttslearn.dsp.logmelspectrogram_to_audio

ttslearn.dsp.logmelspectrogram_to_audio(logmel, sr, n_fft=None, hop_length=None, win_length=None, fmin=None, fmax=None, n_iter=4)[source]

Log-melspectrogram to audio.

Parameters

  • logmel (ndarray) – Log-melspectrogram.

  • sr (int) – Sampling rate.

  • n_fft (int, optional) – FFT size.

  • hop_length (int, optional) – Hop length. Defaults to 12.5ms.

  • win_length (int, optional) – Window length. Defaults to 50 ms.

  • fmin (int, optional) – Minimum frequency. Defaults to 0.

  • fmax (int, optional) – Maximum frequency. Defaults to sr / 2.

  • n_iter (int, optional) – Number of power iterations. Defaults to 4.

Returns

Waveform.

Return type

numpy.ndarray