Acoustic Scene Classification

TL;DR

This paper reviews the state-of-the-art in acoustic scene classification, introduces a benchmark dataset and evaluation framework, compares algorithms including human performance, and identifies significant improvements over baseline methods.

Contribution

It provides a comprehensive framework, benchmark dataset, and evaluation metrics for acoustic scene classification, along with a comparison of algorithms and human accuracy.

Findings

Some algorithms outperform the baseline significantly.

The best algorithm matches human median accuracy.

All scenes are correctly classified by at least some individuals.

Abstract

In this article we present an account of the state-of-the-art in acoustic scene classification (ASC), the task of classifying environments from the sounds they produce. Starting from a historical review of previous research in this area, we define a general framework for ASC and present different imple- mentations of its components. We then describe a range of different algorithms submitted for a data challenge that was held to provide a general and fair benchmark for ASC techniques. The dataset recorded for this purpose is presented, along with the performance metrics that are used to evaluate the algorithms and statistical significance tests to compare the submitted methods. We use a baseline method that employs MFCCS, GMMS and a maximum likelihood criterion as a benchmark, and only find sufficient evidence to conclude that three algorithms significantly outperform it. We also evaluate the human classification accuracy in performing a similar classification task. The best performing algorithm achieves a mean accuracy that matches the median accuracy obtained by humans, and common pairs of classes are misclassified by both computers and humans. However, all acoustic scenes are correctly classified by at least some individuals, while there are scenes that are misclassified by all algorithms.