LEAF: A Learnable Frontend for Audio Classification

TL;DR

This paper introduces a fully learnable audio frontend that surpasses traditional mel-filterbanks and previous learnable methods across diverse audio classification tasks, with fewer parameters and improved performance.

Contribution

The authors propose a lightweight, fully learnable frontend architecture that replaces mel-filterbanks, learning all feature extraction operations for improved audio classification.

Findings

Outperforms mel-filterbanks on multiple audio tasks

Achieves state-of-the-art results on Audioset

Uses significantly fewer parameters than previous methods

Abstract

Mel-filterbanks are fixed, engineered audio features which emulate human perception and have been used through the history of audio understanding up to today. However, their undeniable qualities are counterbalanced by the fundamental limitations of handmade representations. In this work we show that we can train a single learnable frontend that outperforms mel-filterbanks on a wide range of audio signals, including speech, music, audio events and animal sounds, providing a general-purpose learned frontend for audio classification. To do so, we introduce a new principled, lightweight, fully learnable architecture that can be used as a drop-in replacement of mel-filterbanks. Our system learns all operations of audio features extraction, from filtering to pooling, compression and normalization, and can be integrated into any neural network at a negligible parameter cost. We perform multi-task training on eight diverse audio classification tasks, and show consistent improvements of our model over mel-filterbanks and previous learnable alternatives. Moreover, our system outperforms the current state-of-the-art learnable frontend on Audioset, with orders of magnitude fewer parameters.