# Simple Pooling Front-ends For Efficient Audio Classification

arXiv: https://arxiv.org/abs/2210.00943 · HTML: https://mlsanity.com/paper/2210.00943/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 3 Oct 2022.

## Builds on (most cited first, 19 of 19)

- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Speaker Recognition from Raw Waveform with SincNet](https://mlsanity.com/paper/1808.00158/) (2018)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [Spectral Representations for Convolutional Neural Networks](https://mlsanity.com/paper/1506.03767/) (2015)
- [A multi-device dataset for urban acoustic scene classification](https://mlsanity.com/paper/1807.09840/) (2018)
- [LEAF: A Learnable Frontend for Audio Classification](https://mlsanity.com/paper/2101.08596/) (2021)
- [SpecAugment on Large Scale Datasets](https://mlsanity.com/paper/1912.05533/) (2019)
- [Sound Event Detection: A Tutorial](https://mlsanity.com/paper/2107.05463/) (2021)
- [Distilling the Knowledge of BERT for Sequence-to-Sequence ASR](https://mlsanity.com/paper/2008.03822/) (2020)
- [Large-scale weakly supervised audio classification using gated convolutional neural network](https://mlsanity.com/paper/1710.00343/) (2017)
- [Temporal Knowledge Distillation for On-device Audio Classification](https://mlsanity.com/paper/2110.14131/) (2021)
- [Knowledge Distillation for Small-footprint Highway Networks](https://mlsanity.com/paper/1608.00892/) (2016)
- [A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification](https://mlsanity.com/paper/2203.15751/) (2022)
- [Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture](https://mlsanity.com/paper/2007.01696/) (2020)
- [Continual Learning For On-Device Environmental Sound Classification](https://mlsanity.com/paper/2207.07429/) (2022)
- [Deep Neural Decision Forest for Acoustic Scene Classification](https://mlsanity.com/paper/2203.03436/) (2022)
- [Low-complexity CNNs for Acoustic Scene Classification](https://mlsanity.com/paper/2207.11529/) (2022)

## Built on by (most cited first, 9 of 9)

- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis](https://mlsanity.com/paper/2311.08667/) (2023)
- [Learning Temporal Resolution in Spectrogram for Audio Classification](https://mlsanity.com/paper/2210.01719/) (2022)
- [ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions](https://mlsanity.com/paper/2407.08691/) (2024)
- [Ontology-aware Learning and Evaluation for Audio Tagging](https://mlsanity.com/paper/2211.12195/) (2022)
- [From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers](https://mlsanity.com/paper/2401.08415/) (2024)
- [Universal Sound Separation with Self-Supervised Audio Masked Autoencoder](https://mlsanity.com/paper/2407.11745/) (2024)
- [Knowledge Distillation for Efficient Audio-Visual Video Captioning](https://mlsanity.com/paper/2306.09947/) (2023)

## Abstract (arXiv)

Recently, there has been increasing interest in building efficient audio neural networks for on-device scenarios. Most existing approaches are designed to reduce the size of audio neural networks using methods such as model pruning. In this work, we show that instead of reducing model size using complex methods, eliminating the temporal redundancy in the input audio features (e.g., mel-spectrogram) could be an effective approach for efficient audio classification. To do so, we proposed a family of simple pooling front-ends (SimPFs) which use simple non-parametric pooling operations to reduce the redundant information within the mel-spectrogram. We perform extensive experiments on four audio classification tasks to evaluate the performance of SimPFs. Experimental results show that SimPFs can achieve a reduction in more than half of the number of floating point operations (FLOPs) for off-the-shelf audio neural networks, with negligible degradation or even some improvements in audio classification performance.