# Variational Information Bottleneck for Effective Low-resource Audio Classification

arXiv: https://arxiv.org/abs/2107.04803 · HTML: https://mlsanity.com/paper/2107.04803/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2021.

## Built on by (most cited first, 5 of 5)

- [SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning](https://mlsanity.com/paper/2206.13101/) (2022)
- [A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer](https://mlsanity.com/paper/2110.08598/) (2021)
- [Uncertainty Calibration for Deep Audio Classifiers](https://mlsanity.com/paper/2206.13071/) (2022)
- [Augmentation-induced Consistency Regularization for Classification](https://mlsanity.com/paper/2205.12461/) (2022)
- [Boosting Star-GANs for Voice Conversion with Contrastive Discriminator](https://mlsanity.com/paper/2209.10088/) (2022)

## Abstract (arXiv)

Large-scale deep neural networks (DNNs) such as convolutional neural networks (CNNs) have achieved impressive performance in audio classification for their powerful capacity and strong generalization ability. However, when training a DNN model on low-resource tasks, it is usually prone to overfitting the small data and learning too much redundant information. To address this issue, we propose to use variational information bottleneck (VIB) to mitigate overfitting and suppress irrelevant information. In this work, we conduct experiments ona 4-layer CNN. However, the VIB framework is ready-to-use and could be easily utilized with many other state-of-the-art network architectures. Evaluation on a few audio datasets shows that our approach significantly outperforms baseline methods, yielding more than 5.0% improvement in terms of classification accuracy in some low-source settings.