https://www.tensorflow.org/io/tutorials/audio
(Trim the noise, Fade In and Fade Out, Frequency Masking, Time Masking)
https://pytorch.org/tutorials/beginner/audio_preprocessing_tutorial.html#data-augmentation
(Convolution reverb , Adding background noise, MelSpectrogram, TimeStrech)
https://www.tensorflow.org/tutorials/audio/simple_audio NN classifier to classify the audio files into class. Generates spectrogram of each file and use that as input and predicts the specific class.
https://pytorch.org/tutorials/intermediate/speech_command_recognition_with_torchaudio_tutorial.html
NN Based classifier work on raw image + wavefrom to predict the class