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

References in corpus (1)

• Adam: A Method for Stochastic Optimization

Cited by in corpus (12)

• Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events
• Acoustic Scene Classification with Spectrogram Processing Strategies
• Acoustic scene classification using teacher-student learning with soft-labels
• Sound Context Classification Basing on Join Learning Model and Multi-Spectrogram Features
• Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference
• Acoustic Scene Classification Using Fusion of Attentive Convolutional Neural Networks for DCASE2019 Challenge
• ACGAN-based Data Augmentation Integrated with Long-term Scalogram for Acoustic Scene Classification
• Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification
• Enhancing Sound Texture in CNN-Based Acoustic Scene Classification
• Robust Acoustic Domain Identification with its Application to Speaker Diarization
• Additive Phoneme-aware Margin Softmax Loss for Language Recognition
• An Acoustic Segment Model Based Segment Unit Selection Approach to Acoustic Scene Classification with Partial Utterances