# Investigating Multi-Feature Selection and Ensembling for Audio Classification

arXiv: https://arxiv.org/abs/2206.07511 · HTML: https://mlsanity.com/paper/2206.07511/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 47 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 12 of 12)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Rethinking CNN Models for Audio Classification](https://mlsanity.com/paper/2007.11154/) (2020)
- [Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms](https://mlsanity.com/paper/1703.01789/) (2017)
- [Large-scale weakly supervised audio classification using gated convolutional neural network](https://mlsanity.com/paper/1710.00343/) (2017)
- [Locality and Structure Regularized Low Rank Representation for Hyperspectral Image Classification](https://mlsanity.com/paper/1905.02488/) (2019)
- [An Ensemble of Convolutional Neural Networks for Audio Classification](https://mlsanity.com/paper/2007.07966/) (2020)
- [Multi-stream Network With Temporal Attention For Environmental Sound Classification](https://mlsanity.com/paper/1901.08608/) (2019)
- [Multi-Representation Knowledge Distillation For Audio Classification](https://mlsanity.com/paper/2002.09607/) (2020)
- [Multi-Temporal Resolution Convolutional Neural Networks for Acoustic Scene Classification](https://mlsanity.com/paper/1811.04419/) (2018)

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

- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Precise Single-stage Detector](https://mlsanity.com/paper/2210.04252/) (2022)
- [Random Data Augmentation based Enhancement: A Generalized Enhancement Approach for Medical Datasets](https://mlsanity.com/paper/2210.00824/) (2022)
- [AudRandAug: Random Image Augmentations for Audio Classification](https://mlsanity.com/paper/2309.04762/) (2023)
- [KeepOriginalAugment: Single Image-based Better Information-Preserving Data Augmentation Approach](https://mlsanity.com/paper/2405.06354/) (2024)
- [Data Dimension Reduction makes ML Algorithms efficient](https://mlsanity.com/paper/2211.09392/) (2022)
- [Advanced Audio Aid for Blind People](https://mlsanity.com/paper/2212.00004/) (2022)
- [FaceSaliencyAug: Mitigating Geographic, Gender and Stereotypical Biases via Saliency-Based Data Augmentation](https://mlsanity.com/paper/2410.14070/) (2024)
- [Saliency-Based diversity and fairness Metric and FaceKeepOriginalAugment: A Novel Approach for Enhancing Fairness and Diversity](https://mlsanity.com/paper/2411.00831/) (2024)

## Abstract (arXiv)

Deep Learning (DL) algorithms have shown impressive performance in diverse domains. Among them, audio has attracted many researchers over the last couple of decades due to some interesting patterns--particularly in classification of audio data. For better performance of audio classification, feature selection and combination play a key role as they have the potential to make or break the performance of any DL model. To investigate this role, we conduct an extensive evaluation of the performance of several cutting-edge DL models (i.e., Convolutional Neural Network, EfficientNet, MobileNet, Supper Vector Machine and Multi-Perceptron) with various state-of-the-art audio features (i.e., Mel Spectrogram, Mel Frequency Cepstral Coefficients, and Zero Crossing Rate) either independently or as a combination (i.e., through ensembling) on three different datasets (i.e., Free Spoken Digits Dataset, Audio Urdu Digits Dataset, and Audio Gujarati Digits Dataset). Overall, results suggest feature selection depends on both the dataset and the model. However, feature combinations should be restricted to the only features that already achieve good performances when used individually (i.e., mostly Mel Spectrogram, Mel Frequency Cepstral Coefficients). Such feature combination/ensembling enabled us to outperform the previous state-of-the-art results irrespective of our choice of DL model.