Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices

TL;DR

This paper introduces a simple, effective method for acoustic scene classification that improves generalization across different recording devices, even with limited data, by addressing device mismatch issues.

Contribution

It proposes a novel approach for device mismatch correction in audio classification, applicable with minimal data and compatible with time and frequency domain features.

Findings

Achieved 75% accuracy in DCASE 2019 challenge scenario.

Method outperforms baseline in device mismatch situations.

Works effectively with very few training examples.

Abstract

Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward method is introduced to address this problem. Two variants of the approach are presented. First requires aligned examples from multiple devices, the second approach alleviates this requirement. This method works for both time and frequency domain representations of audio recordings. Further, a relation to standardization and Cepstral Mean Subtraction is analysed. The proposed approach becomes effective even when very few examples are provided. This method was developed during the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and won the 1st place in the scenario with mis-matched recording devices with the accuracy of 75%. Source code for the experiments can be found online.