# Data-Balanced Curriculum Learning for Audio Question Answering

Source: [Data-Balanced Curriculum Learning for Audio Question Answering](<https://www.sota2.com/research/paper/68fa79ea1e209131cea7fef3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:07:32.191Z

Authors: Gijs Wijngaard, Elia Formisano, Michele Esposito, Michel Dumontier

Published: 2025-07-09T13:06:14.000Z

## Abstract

Audio question answering (AQA) requires models to understand acoustic content and perform complex reasoning. Current models struggle with dataset imbalances and unstable training dynamics. This work combines curriculum learning with statistical data balancing to address these challenges. The method labels question difficulty using language models, then trains progressively from easy to hard examples. Statistical filtering removes overrepresented audio categories, and guided decoding constrains outputs to valid multiple-choice formats. Experiments on the DCASE 2025 training set and five additional public datasets show that data curation improves accuracy by 11.7% over baseline models, achieving 64.2% on the DCASE 2025 benchmark.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.06815>)

[PDF](<https://arxiv.org/pdf/2507.06815.pdf>)