# A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification

arXiv: https://arxiv.org/abs/2607.01974 · HTML: https://mlsanity.com/paper/2607.01974/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Data Augmentation using Random Image Cropping and Patching for Deep CNNs](https://mlsanity.com/paper/1811.09030/) (2018)
- [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023)
- [Nearest Neighbor Knowledge Distillation for Neural Machine Translation](https://mlsanity.com/paper/2205.00479/) (2022)
- [Learning Identity Mappings with Residual Gates](https://mlsanity.com/paper/1611.01260/) (2016)
- [KNN-enhanced Deep Learning Against Noisy Labels](https://mlsanity.com/paper/2012.04224/) (2020)
- [Heterogeneous sound classification with the Broad Sound Taxonomy and Dataset](https://mlsanity.com/paper/2410.00980/) (2024)

## Abstract (arXiv)

This technical report describes our system for Task 1 of the DCASE 2026 Challenge, which aims to classify heterogeneous audio recordings according to the Broad Sound Taxonomy (BST). The task requires both accurate second-level prediction and consistency with the top-level taxonomy. Our system is built on CLAP-based audio-text representations and is improved along three strategies: expanding the training set with a filtered subset of BSD35k, enhancing acoustic modeling with feature-specific branches, and refining predictions using hierarchy-aware classifiers and KNN-based post-processing. Among the acoustic features considered, the log-STFT branch provides the strongest single-model performance. With KNN-based post-processing, our best single system achieves a hierarchical F1 score (Hier. F1) of 80.84% on the BSD10k-v1.2 set under the same evaluation protocol as the baseline. We further construct ensemble systems by combining models with complementary acoustic features and classification heads, achieving Hier. F1 scores of 81.25% and 81.18%, respectively.