# Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data

arXiv: https://arxiv.org/abs/2110.14425 · HTML: https://mlsanity.com/paper/2110.14425/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 27 Oct 2021.

## Builds on (most cited first, 8 of 8)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation](https://mlsanity.com/paper/2010.16061/) (2020)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [Partial AUC optimization based deep speaker embeddings with class-center learning for text-independent speaker verification](https://mlsanity.com/paper/1911.08077/) (2019)
- [Optimization of the Area Under the ROC Curve using Neural Network Supervectors for Text-Dependent Speaker Verification](https://mlsanity.com/paper/1901.11332/) (2019)
- [Speaker Verification By Partial AUC Optimization With Mahalanobis Distance Metric Learning](https://mlsanity.com/paper/1902.00889/) (2019)

## Built on by (most cited first, 2 of 2)

- [FusionVision: A comprehensive approach of 3D object reconstruction and segmentation from RGB-D cameras using YOLO and fast segment anything](https://mlsanity.com/paper/2403.00175/) (2024)
- [Acoustic scattering AI for non-invasive object classifications: A case study on hair assessment](https://mlsanity.com/paper/2506.14148/) (2025)

## Abstract (arXiv)

Area under the ROC curve (AUC) optimisation techniques developed for neural networks have recently demonstrated their capabilities in different audio and speech related tasks. However, due to its intrinsic nature, AUC optimisation has focused only on binary tasks so far. In this paper, we introduce an extension to the AUC optimisation framework so that it can be easily applied to an arbitrary number of classes, aiming to overcome the issues derived from training data limitations in deep learning solutions. Building upon the multiclass definitions of the AUC metric found in the literature, we define two new training objectives using a one-versus-one and a one-versus-rest approach. In order to demonstrate its potential, we apply them in an audio segmentation task with limited training data that aims to differentiate 3 classes: foreground music, background music and no music. Experimental results show that our proposal can improve the performance of audio segmentation systems significantly compared to traditional training criteria such as cross entropy.