paddlespeech.vector.io.signal_processing module

paddlespeech.vector.io.signal_processing.blackman_window(win_len, dtype=<class 'numpy.float32'>)

paddlespeech.vector.io.signal_processing.compute_amplitude(waveforms, lengths=None, amp_type='avg', scale='linear')

paddlespeech.vector.io.signal_processing.convolve1d(waveform, kernel, padding=0, pad_type='constant', stride=1, groups=1)

paddlespeech.vector.io.signal_processing.dB_to_amplitude(SNR)

paddlespeech.vector.io.signal_processing.normalize(waveforms, lengths=None, amp_type='avg', eps=1e-14)

paddlespeech.vector.io.signal_processing.notch_filter(notch_freq, filter_width=101, notch_width=0.05)

paddlespeech.vector.io.signal_processing.rescale(waveforms, lengths, target_lvl, amp_type='avg', scale='linear')

paddlespeech.vector.io.signal_processing.reverberate(waveforms, rir_waveform, sample_rate, impulse_duration=0.3, rescale_amp='avg')