# Device-Robust Acoustic Scene Classification via Impulse Response Augmentation

arXiv: https://arxiv.org/abs/2305.07499 · HTML: https://mlsanity.com/paper/2305.07499/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 12 May 2023.

## Builds on (most cited first, 14 of 14)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [Generalized Sliced Wasserstein Distances](https://mlsanity.com/paper/1902.00434/) (2019)
- [Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutions](https://mlsanity.com/paper/2005.14623/) (2020)
- [Building and Evaluation of a Real Room Impulse Response Dataset](https://mlsanity.com/paper/1811.06795/) (2018)
- [The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification](https://mlsanity.com/paper/1907.01803/) (2019)
- [Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks](https://mlsanity.com/paper/2105.12395/) (2021)
- [Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification](https://mlsanity.com/paper/2206.12513/) (2022)
- [Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems](https://mlsanity.com/paper/2105.13734/) (2021)
- [Low-complexity acoustic scene classification in DCASE 2022 Challenge](https://mlsanity.com/paper/2206.03835/) (2022)
- [QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design](https://mlsanity.com/paper/2206.13909/) (2022)
- [Robust Speech Recognition Using Generative Adversarial Networks](https://mlsanity.com/paper/1711.01567/) (2017)
- [Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification](https://mlsanity.com/paper/1909.02869/) (2019)

## Built on by (most cited first, 11 of 11)

- [Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds](https://mlsanity.com/paper/2509.04166/) (2025)
- [Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models](https://mlsanity.com/paper/2310.15648/) (2023)
- [Data Efficient Acoustic Scene Classification using Teacher-Informed Confusing Class Instruction](https://mlsanity.com/paper/2409.11964/) (2024)
- [Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification](https://mlsanity.com/paper/2503.11363/) (2025)
- [SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures](https://mlsanity.com/paper/2504.10793/) (2025)
- [Improving Acoustic Scene Classification with City Features](https://mlsanity.com/paper/2503.16862/) (2025)
- [Acoustic Scene Classification Using CNN-GRU Model Without Knowledge Distillation](https://mlsanity.com/paper/2509.09931/) (2025)
- [An Entropy-Guided Curriculum Learning Strategy for Data-Efficient Acoustic Scene Classification under Domain Shift](https://mlsanity.com/paper/2509.11168/) (2025)
- [Lightweight and Generalizable Acoustic Scene Representations via Contrastive Fine-Tuning and Distillation](https://mlsanity.com/paper/2510.03728/) (2025)
- ["OK Aura, Be Fair With Me": Demographics-Agnostic Training for Bias Mitigation in Wake-up Word Detection](https://mlsanity.com/paper/2604.05830/) (2026)
- [A Strength-Monotonic Law for Domain Alignment in Frozen-Embedding Bioacoustic Classification](https://mlsanity.com/paper/2610.09737/) (2026)

## Abstract (arXiv)

The ability to generalize to a wide range of recording devices is a crucial performance factor for audio classification models. The characteristics of different types of microphones introduce distributional shifts in the digitized audio signals due to their varying frequency responses. If this domain shift is not taken into account during training, the model's performance could degrade severely when it is applied to signals recorded by unseen devices. In particular, training a model on audio signals recorded with a small number of different microphones can make generalization to unseen devices difficult. To tackle this problem, we convolve audio signals in the training set with pre-recorded device impulse responses (DIRs) to artificially increase the diversity of recording devices. We systematically study the effect of DIR augmentation on the task of Acoustic Scene Classification using CNNs and Audio Spectrogram Transformers. The results show that DIR augmentation in isolation performs similarly to the state-of-the-art method Freq-MixStyle. However, we also show that DIR augmentation and Freq-MixStyle are complementary, achieving a new state-of-the-art performance on signals recorded by devices unseen during training.