Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events
Preprint
Abstract
In this paper, we propose a new strategy for acoustic scene classification (ASC) , namely recognizing acoustic scenes through identifying distinct sound events. This differs from existing strategies, which focus on characterizing global acoustical distributions of audio or the temporal evolution of short-term audio features, without analysis down to the level of sound events. To identify distinct sound events for each scene, we formulate ASC in a multi-instance learning (MIL) framework, where each audio recording is mapped into a bag-of-instances representation. Here, instances can be seen as high-level representations for sound events inside a scene. We also propose a MIL neural networks model, which implicitly identifies distinct instances (i.e., sound events). Furthermore, we propose two specially designed modules that model the multi-temporal scale and multi-modal natures of the sound events respectively. The experiments were conducted on the official development set of the DCASE2018 Task1 Subtask B, and our best-performing model improves over the official baseline by 9.4% (68.3% vs 58.9%) in terms of classification accuracy. This study indicates that recognizing acoustic scenes by identifying distinct sound events is effective and paves the way for future studies that combine this strategy with previous ones.Keywords
All Related Versions
- Version 1, 2019-04-10, ArXiv
- Version 2, 2019-04-27, ArXiv
- Published version: , 3860.
This publication has 11 references indexed in Scilit:
- A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling2019
- Adaptive Pooling Operators for Weakly Labeled Sound Event DetectionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2018
- Feature Learning With Matrix Factorization Applied to Acoustic Scene ClassificationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Enhanced LBP texture features from time frequency representations for acoustic scene classification2017
- Acoustic Scene Classification: Classifying environments from the sounds they produceIEEE Signal Processing Magazine, 2015
- Histogram of gradients of Time-Frequency Representations for Audio Scene DetectionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Multiple instance classification: Review, taxonomy and comparative studyArtificial Intelligence, 2013
- Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approachThe Journal of the Acoustical Society of America, 2012
- The bag-of-frames approach to audio pattern recognition: A sufficient model for urban soundscapes but not for polyphonic musicThe Journal of the Acoustical Society of America, 2007
- A flexible framework for key audio effects detection and auditory context inferenceIEEE Transactions on Audio, Speech, and Language Processing, 2006