Convolutional Neural Networks and x-vector Embedding for DCASE2018 Acoustic Scene Classification Challenge

TL;DR

This paper presents a fusion of 2D CNNs and 1D x-vector CNNs using log mel-spectrogram and CQT features for acoustic scene classification, achieving third place in the DCASE2018 challenge.

Contribution

It introduces a novel combination of CNN topologies and feature types for improved acoustic scene classification performance.

Findings

Fusion of CNN topologies improves accuracy.

Log mel-spectrogram and CQT features both effective.

Achieved third place in DCASE2018 challenge.

Abstract

In this paper, the Brno University of Technology (BUT) team submissions for Task 1 (Acoustic Scene Classification, ASC) of the DCASE-2018 challenge are described. Also, the analysis of different methods on the leaderboard set is provided. The proposed approach is a fusion of two different Convolutional Neural Network (CNN) topologies. The first one is the common two-dimensional CNNs which is mainly used in image classification. The second one is a one-dimensional CNN for extracting fixed-length audio segment embeddings, so called x-vectors, which has also been used in speech processing, especially for speaker recognition. In addition to the different topologies, two types of features were tested: log mel-spectrogram and CQT features. Finally, the outputs of different systems are fused using a simple output averaging in the best performing system. Our submissions ranked third among 24 teams in the ASC sub-task A (task1a).