Apply MixUp, CutMix, and combination of both to audio waveforms before converting to Spectrogram or MelSpectrogram

class AudioMixHandler[source]

AudioMixHandler(alpha=0.5, stack_y=True) :: MixHandler

Mixup base for TensorAudio

class AudioMixUp[source]

AudioMixUp(alpha=0.5, stack_y=True) :: AudioMixHandler

Implementation of https://arxiv.org/abs/1710.09412 for TensorAudio

class AudioCutMix[source]

AudioCutMix(alpha=1.0, stack_y=True) :: AudioMixHandler

Implementation of https://arxiv.org/abs/1710.09412 for TensorAudio

class AudioCutMixUp[source]

AudioCutMixUp(mix_alpha=0.4, cut_alpha=1.0, stack_y=True, cut_ratio=1, mix_ratio=1) :: AudioMixUp

Implementation of Mixup or CutMix for TensorAudio

class AudioCutMixUpAugment[source]

AudioCutMixUpAugment(mix_alpha=0.4, cut_alpha=1.0, stack_y=True, aug_ratio=1, cut_ratio=1, mix_ratio=1, augs_only=None, wave_augs=False) :: AudioMixUp

Implementation of Mixup, CutMix, or Augment for TensorAudio