# Data Efficient Acoustic Scene Classification using Teacher-Informed Confusing Class Instruction

arXiv: https://arxiv.org/abs/2409.11964 · HTML: https://mlsanity.com/paper/2409.11964/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 8 of its 11 references that are in the map.
- First posted on arXiv 18 Sep 2024.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

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

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutions](https://mlsanity.com/paper/2005.14623/) (2020)
- [Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification](https://mlsanity.com/paper/2206.12513/) (2022)
- [Device-Robust Acoustic Scene Classification via Impulse Response Augmentation](https://mlsanity.com/paper/2305.07499/) (2023)
- [Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge](https://mlsanity.com/paper/2405.10018/) (2024)
- [FocusNet: Classifying Better by Focusing on Confusing Classes](https://mlsanity.com/paper/2110.07307/) (2021)

## Built on by (most cited first, 1 of 1)

- [Joint Feature and Output Distillation for Low-complexity Acoustic Scene Classification](https://mlsanity.com/paper/2507.19557/) (2025)

## Abstract (arXiv)

In this technical report, we describe the SNTL-NTU team's submission for Task 1 Data-Efficient Low-Complexity Acoustic Scene Classification of the detection and classification of acoustic scenes and events (DCASE) 2024 challenge. Three systems are introduced to tackle training splits of different sizes. For small training splits, we explored reducing the complexity of the provided baseline model by reducing the number of base channels. We introduce data augmentation in the form of mixup to increase the diversity of training samples. For the larger training splits, we use FocusNet to provide confusing class information to an ensemble of multiple Patchout faSt Spectrogram Transformer (PaSST) models and baseline models trained on the original sampling rate of 44.1 kHz. We use Knowledge Distillation to distill the ensemble model to the baseline student model. Training the systems on the TAU Urban Acoustic Scene 2022 Mobile development dataset yielded the highest average testing accuracy of (62.21, 59.82, 56.81, 53.03, 47.97)% on split (100, 50, 25, 10, 5)% respectively over the three systems.