# Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization

arXiv: https://arxiv.org/abs/2111.06531 · HTML: https://mlsanity.com/paper/2111.06531/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 12 Nov 2021.

## Builds on (most cited first, 18 of 18)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks](https://mlsanity.com/paper/1805.07925/) (2018)
- [Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutions](https://mlsanity.com/paper/2005.14623/) (2020)
- [Broadcasted Residual Learning for Efficient Keyword Spotting](https://mlsanity.com/paper/2106.04140/) (2021)
- [Feature Fusion for Online Mutual Knowledge Distillation](https://mlsanity.com/paper/1904.09058/) (2019)
- [Trainable Frontend For Robust and Far-Field Keyword Spotting](https://mlsanity.com/paper/1607.05666/) (2016)
- [The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification](https://mlsanity.com/paper/1907.01803/) (2019)
- [Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems](https://mlsanity.com/paper/2105.13734/) (2021)
- [Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation](https://mlsanity.com/paper/2007.08389/) (2020)
- [SubSpectral Normalization for Neural Audio Data Processing](https://mlsanity.com/paper/2103.13620/) (2021)
- [SubSpectralNet - Using Sub-Spectrogram based Convolutional Neural Networks for Acoustic Scene Classification](https://mlsanity.com/paper/1810.12642/) (2018)
- [Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling](https://mlsanity.com/paper/1907.06639/) (2019)
- [Arbitrary Style Transfer using Graph Instance Normalization](https://mlsanity.com/paper/2010.02560/) (2020)

## Built on by (most cited first, 6 of 6)

- [Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting](https://mlsanity.com/paper/2206.13691/) (2022)
- [Phase-driven Domain Generalizable Learning for Nonstationary Time Series](https://mlsanity.com/paper/2402.05960/) (2024)
- [Domain Agnostic Few-shot Learning for Speaker Verification](https://mlsanity.com/paper/2206.13700/) (2022)
- [Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training](https://mlsanity.com/paper/2402.04805/) (2024)
- [Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation](https://mlsanity.com/paper/2303.00550/) (2023)
- [MUST: A Multilingual Student-Teacher Learning approach for low-resource speech recognition](https://mlsanity.com/paper/2310.18865/) (2023)

## Abstract (arXiv)

It is a practical research topic how to deal with multi-device audio inputs by a single acoustic scene classification system with efficient design. In this work, we propose Residual Normalization, a novel feature normalization method that uses frequency-wise normalization % instance normalization with a shortcut path to discard unnecessary device-specific information without losing useful information for classification. Moreover, we introduce an efficient architecture, BC-ResNet-ASC, a modified version of the baseline architecture with a limited receptive field. BC-ResNet-ASC outperforms the baseline architecture even though it contains the small number of parameters. Through three model compression schemes: pruning, quantization, and knowledge distillation, we can reduce model complexity further while mitigating the performance degradation. The proposed system achieves an average test accuracy of 76.3% in TAU Urban Acoustic Scenes 2020 Mobile, development dataset with 315k parameters, and average test accuracy of 75.3% after compression to 61.0KB of non-zero parameters. The proposed method won the 1st place in DCASE 2021 challenge, TASK1A.