mlsanityData to 7 Oct 2026

EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use

arXiv 2207.05508 ↗First posted 12 Jul 2022cs.SD cs.LG eess.AScited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 11 of its 20 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

11 of 20 references.

References · 11

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  2. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  3. 2021AST: Audio Spectrogram Transformercited by 634
  4. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 563
  5. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  6. 2021LEAF: A Learnable Frontend for Audio Classificationcited by 69
  7. 2016Trainable Frontend For Robust and Far-Field Keyword Spottingcited by 32
  8. 2017Learning Filterbanks from Raw Speech for Phone Recognitioncited by 25
  9. 2017End-to-end learning for music audio tagging at scalecited by 25
  10. 2013Estimating Phoneme Class Conditional Probabilities from Raw Speech Signal using Convolutional Neural Networkscited by 9
  11. 2020Exploring Filterbank Learning for Keyword Spottingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 2; 2026: 1.

8 papers.

  1. 2023Fitting Auditory Filterbanks with Multiresolution Neural Networkscited by 4
  2. 2023Instabilities in Convnets for Raw Audiocited by 2
  3. 2024Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognitioncited by 1
  4. 2026The Caf'e in Amsterdam: When the Incumbent Becomes the Oraclecited by 1
  5. 2024Towards Enhanced Classification of Abnormal Lung sound in Multi-breath: A Light Weight Multi-label and Multi-head Attention Classification Methodcited by 0
  6. 2024Raw Audio Classification with Cosine Convolutional Neural Network (CosCovNN)cited by 0
  7. 2025Acoustic Classification of Maritime Vessels using Learnable Filterbankscited by 0
  8. 2025AaSP: Aliasing-aware Self-Supervised Pre-Training for Audio Spectrogram Transformerscited by 0