DCASE 2022: Comparative Analysis Of CNNs For Acoustic Scene Classification Under Low-Complexity Considerations

TL;DR

This paper compares CNN and Conv-mixer architectures for acoustic scene classification, emphasizing low-complexity solutions suitable for IoT devices, and finds CNN performs better despite Conv-mixer's lighter design.

Contribution

It provides a comparative analysis of CNN and Conv-mixer architectures specifically for low-complexity acoustic scene classification tasks.

Findings

CNN outperforms Conv-mixer by 8 percentage points.

Conv-mixer architectures are lighter but less accurate.

Both architectures surpass the baseline performance.

Abstract

Acoustic scene classification is an automatic listening problem that aims to assign an audio recording to a pre-defined scene based on its audio data. Over the years (and in past editions of the DCASE) this problem has often been solved with techniques known as ensembles (use of several machine learning models to combine their predictions in the inference phase). While these solutions can show performance in terms of accuracy, they can be very expensive in terms of computational capacity, making it impossible to deploy them in IoT devices. Due to the drift in this field of study, this task has two limitations in terms of model complexity. It should be noted that there is also the added complexity of mismatching devices (the audios provided are recorded by different sources of information). This technical report makes a comparative study of two different network architectures: conventional CNN and Conv-mixer. Although both networks exceed the baseline required by the competition, the conventional CNN shows a higher performance, exceeding the baseline by 8 percentage points. Solutions based on Conv-mixer architectures show worse performance although they are much lighter solutions.