Domain Information Control at Inference Time for Acoustic Scene Classification

by   Shahed Masoudian, et al.

Domain shift is considered a challenge in machine learning as it causes significant degradation of model performance. In the Acoustic Scene Classification task (ASC), domain shift is mainly caused by different recording devices. Several studies have already targeted domain generalization to improve the performance of ASC models on unseen domains, such as new devices. Recently, the Controllable Gate Adapter ConGater has been proposed in Natural Language Processing to address the biased training data problem. ConGater allows controlling the debiasing process at inference time. ConGater's main advantage is the continuous and selective debiasing of a trained model, during inference. In this work, we adapt ConGater to the audio spectrogram transformer for an acoustic scene classification task. We show that ConGater can be used to selectively adapt the learned representations to be invariant to device domain shifts such as recording devices. Our analysis shows that ConGater can progressively remove device information from the learned representations and improve the model generalization, especially under domain shift conditions (e.g. unseen devices). We show that information removal can be extended to both device and location domain. Finally, we demonstrate ConGater's ability to enhance specific device performance without further training.


page 1

page 4


Device-Robust Acoustic Scene Classification via Impulse Response Augmentation

The ability to generalize to a wide range of recording devices is a cruc...

Over-Parameterization and Generalization in Audio Classification

Convolutional Neural Networks (CNNs) have been dominating classification...

Unsupervised adversarial domain adaptation for acoustic scene classification

A general problem in acoustic scene classification task is the mismatche...

Shape Guided Gradient Voting for Domain Generalization

Domain generalization aims to address the domain shift between training ...

On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers

Varying conditions between the data seen at training and at application ...

Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification

Distribution mismatches between the data seen at training and at applica...

Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification

A challenging problem in deep learning-based machine listening field is ...

Please sign up or login with your details

Forgot password? Click here to reset