Audio Deep Learning Made Simple: Sound Classification, Step-by-Step

By Medium - 2021-03-18

Description

An end-to-end example and architecture for Audio Deep Learning’s foundational application scenario, in Plain English.

Summary

  • Audio Deep Learning Made Simple: The augmented audio is now converted into a Mel Spectrogram, resulting in a shape of (num_channels, Mel freq_bands, time_steps) = (2, 64, 344) The SpecAugment data augmentation now randomly applies Time and Frequency Masks to the Mel Spectrograms.
  • Each batch has a shape of (batch_sz, num_channels, Mel freq_bands, time_steps) A batch of (X, y) data We can visualize one item from the batch.
  • Conclusion We have now seen an end-to-end example of sound classification which is one of the most foundational problems in audio deep learning.

 

Topics

  1. Backend (0.4)
  2. Machine_Learning (0.28)
  3. Database (0.16)

Similar Articles

Data Science Learning Roadmap for 2021

By freeCodeCamp.org - 2021-01-12

Although nothing really changes but the date, a new year fills everyone with the hope of starting things afresh. If you add in a bit of planning, some well-envisioned goals, and a learning roadmap, yo ...

Introduction to Active Learning

By KDnuggets - 2020-12-15

An extensive overview of Active Learning, with an explanation into how it works and can assist with data labeling, as well as its performance and potential limitations.