Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classification
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to get domain-invariant features. However, unlike image processing, we analyze that domain-relevant information in an audio feature is dominant in frequency statistics rather than channel statistics. Motivated by our analysis, we introduce Relaxed Instance Frequency-wise Normalization (RFN): a plug-and-play, explicit normalization module along the frequency axis which can eliminate instance-specific domain discrepancy in an audio feature while relaxing undesirable loss of useful discriminative information. Empirically, simply adding RFN to networks shows clear margins compared to previous domain generalization approaches on acoustic scene classification and yields improved robustness for multiple audio devices. Especially, the proposed RFN won the DCASE2021 challenge TASK1A, low-complexity acoustic scene classification with multiple devices, with a clear margin, and RFN is an extended work of our technical report.
Code (0)
등록된 구현이 없습니다.
Tasks
Acoustic Scene ClassificationDomain GeneralizationScene ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Bayesian Learning for Domain-Invariant Speaker Verification and Anti-Spoofing
The performance of automatic speaker verification (ASV) and anti-spoofing drops seriously under real-world domain mismatch conditions. The relaxed instance frequency-wise normalization (RFN), which normalizes the frequen…
Speaker VerificationVariational InferenceFrequency Disentangled Features in Neural Image Compression
The design of a neural image compression network is governed by how well the entropy model matches the true distribution of the latent code. Apart from the model capacity, this ability is indirectly under the effect of h…
DisentanglementImage CompressionQuantizationDomain Generalization via Frequency-domain-based Feature Disentanglement and Interaction
Adaptation to out-of-distribution data is a meta-challenge for all statistical learning algorithms that strongly rely on the i.i.d. assumption. It leads to unavoidable labor costs and confidence crises in realistic appli…
Data AugmentationDecoderDisentanglementDomain Generalization+1Towards Robust Domain Generalization in 2D Neural Audio Processing
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to ge…
Acoustic Scene ClassificationDomain GeneralizationKeyword SpottingScene Classification+1Generalized UAV Object Detection via Frequency Domain Disentanglement
When deploying the Unmanned Aerial Vehicles object detection (UAV-OD) network to complex and unseen real-world scenarios, the generalization ability is usually reduced due to the domain shift. To address this issue, …
DisentanglementObjectobject-detectionObject Detection