LEAF: A Learnable Frontend for Audio Classification

By Google AI Blog - 2021-03-12

Description

Posted by Neil Zeghidour, Research Scientist, Google Research Developing machine learning (ML) models for audio understanding has seen tr...

Summary

  • Developing machine learning (ML) models for audio understanding has seen tremendous progress over the past several years.
  • As a consequence, standard mel filterbanks are used for most audio classification tasks in practice, even though they are suboptimal.
  • Mimicking Human Perception of Sound The first step in the traditional approach to creating a mel filterbank is to capture the sound’s time-variability by windowing, i.e., cutting the signal into short segments with fixed duration.
  • This way, even when paired with a small classifier, such as EfficientNetB0, the LEAF model only accounts for 0.01% of the total parameters.

 

Topics

  1. Machine_Learning (0.24)
  2. NLP (0.24)
  3. Backend (0.1)

Similar Articles

CLIP: Connecting Text and Images

By OpenAI - 2021-01-05

We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision.