Audio-Data-Augmentation

Audio Data Augmentation using Librosa

Librosa is a python package for music and audio analysis. It provides the building blocks necessary to create music information retrieval systems. I used Librosa to scale the amplitude, frequency, speed of this audio piece and add some white noise to it.

Original Audio:

053.mp4

Information Retrieved from the audio

Transcript: Adding fast leads to wrong sum

Spectrum:

Adding white noise:

augmented_audio.mp4

Slowing down the audio:

stretched_audio.mp4

Increasing the pitch:

higher_pitch_audio.mp4

Increasing the Volume:

louder_audio.mp4