Acoustic Scene Clustering Using Joint Optimization of Deep Embedding Learning and Clustering Iteration

TL;DR

This paper introduces a novel acoustic scene clustering method that jointly optimizes deep feature learning and clustering, achieving superior results over existing unsupervised approaches.

Contribution

It proposes a unified framework combining deep CNN-based feature extraction with hierarchical clustering, optimized through a joint loss function.

Findings

Outperforms other unsupervised methods in clustering accuracy

Deep embedding features outperform state-of-the-art features

Unified optimization improves clustering performance

Abstract

Recent efforts have been made on acoustic scene classification in the audio signal processing community. In contrast, few studies have been conducted on acoustic scene clustering, which is a newly emerging problem. Acoustic scene clustering aims at merging the audio recordings of the same class of acoustic scene into a single cluster without using prior information and training classifiers. In this study, we propose a method for acoustic scene clustering that jointly optimizes the procedures of feature learning and clustering iteration. In the proposed method, the learned feature is a deep embedding that is extracted from a deep convolutional neural network (CNN), while the clustering algorithm is the agglomerative hierarchical clustering (AHC). We formulate a unified loss function for integrating and optimizing these two procedures. Various features and methods are compared. The experimental results demonstrate that the proposed method outperforms other unsupervised methods in terms of the normalized mutual information and the clustering accuracy. In addition, the deep embedding outperforms many state-of-the-art features.