EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use

Jan Schlüter, Gerald Gutenbrunner
7/12/2022
cs.SDcs.LGeess.AS

No official code found. Best implementation: CPJKU/EfficientLEAF (53 stars, MIT, last commit 2022-12-09).

Abstract

In audio classification, differentiable auditory filterbanks with few parameters cover the middle ground between hard-coded spectrograms and raw audio. LEAF (arXiv:2101.08596), a Gabor-based filterbank combined with Per-Channel Energy Normalization (PCEN), has shown promising results, but is computationally expensive. With inhomogeneous convolution kernel sizes and strides, and by replacing PCEN with better parallelizable operations, we can reach similar results more efficiently. In experiments on six audio classification tasks, our frontend matches the accuracy of LEAF at 3% of the cost, but both fail to consistently outperform a fixed mel filterbank. The quest for learnable audio frontends is not solved.

View on arXivView PDF

Code Implementations(1)

CPJKU/EfficientLEAFCommunity100%
MIT

Official implementation of EfficientLEAF, a learnable audio frontend.

538Shell, PythonJul 12, 20223 years agoMIT

Similar Papers

LEAF: A Learnable Frontend for Audio Classification

91% match1 repo5302021

Studying the Effect of Audio Filters in Pre-Trained Models for Environmental Sound Classification

86% match2024

Transformer-based Sequence Labeling for Audio Classification based on MFCCs

85% match2023

Raw Audio Classification with Cosine Convolutional Neural Network (CosCovNN)

85% match2024

LCANets++: Robust Audio Classification using Multi-layer Neural Networks with Lateral Competition

84% match2023

End-to-End Environmental Sound Classification using a 1D Convolutional Neural Network

84% match2019

Cite this paper

@article{schlter2022efficientleaf,
  title  = {EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use},
  author = {Jan Schlüter and Gerald Gutenbrunner},
  year   = {2022},
  eprint = {2207.05508},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.05508v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.05508.svg)](https://codeofpaper.com/paper/2207.05508)

Discussion