Acoustic Scene Classification

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.

Cited by in corpus (51)

• Machine learning in acoustics: theory and applications
• Sound Event Detection: A Tutorial
• SoundNet: Learning Sound Representations from Unlabeled Video
• A multi-device dataset for urban acoustic scene classification
• Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019
• WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research
• Automated Audio Captioning: An Overview of Recent Progress and New Challenges
• Acoustic scene classification using convolutional neural network and multiple-width frequency-delta data augmentation
• Label Tree Embeddings for Acoustic Scene Classification
• CAA-Net: Conditional Atrous CNNs with Attention for Explainable Device-robust Acoustic Scene Classification
• AI-based soundscape analysis: Jointly identifying sound sources and predicting annoyance
• Few-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypes
• The bag-of-frames approach: a not so sufficient model for urban soundscapes
• Mosquito detection with low-cost smartphones: data acquisition for malaria research
• Hierarchical learning for DNN-based acoustic scene classification
• The NTT DCASE2020 Challenge Task 6 system: Automated Audio Captioning with Keywords and Sentence Length Estimation
• Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval
• A Squeeze-and-Excitation and Transformer based Cross-task System for Environmental Sound Recognition
• Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events
• Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification
• A Compact and Discriminative Feature Based on Auditory Summary Statistics for Acoustic Scene Classification
• Effects of Word-frequency based Pre- and Post- Processings for Audio Captioning
• The Study of Urban Residential's Public Space Activeness using Space-centric Approach
• Attention based Convolutional Recurrent Neural Network for Environmental Sound Classification
• TF-SepNet: An Efficient 1D Kernel Design in CNNs for Low-Complexity Acoustic Scene Classification
• Inferring Room Semantics Using Acoustic Monitoring
• Sound event detection via dilated convolutional recurrent neural networks
• Representations of Sound in Deep Learning of Audio Features from Music
• Cost-sensitive detection with variational autoencoders for environmental acoustic sensing
• ACGAN-based Data Augmentation Integrated with Long-term Scalogram for Acoustic Scene Classification
• Data-Efficient Low-Complexity Acoustic Scene Classification via Distilling and Progressive Pruning
• An efficient supervised dictionary learning method for audio signal recognition
• Quantum-Enhanced Transformers for Robust Acoustic Scene Classification in IoT Environments
• Learning Frame Level Attention for Environmental Sound Classification
• A Curated Dataset of Urban Scenes for Audio-Visual Scene Analysis
• Definition-independent Formalization of Soundscapes: Towards a Formal Methodology
• DcaseNet: An integrated pretrained deep neural network for detecting and classifying acoustic scenes and events
• WSNet: Compact and Efficient Networks Through Weight Sampling
• Cross-task pre-training for on-device acoustic scene classification
• Characterizing dynamically varying acoustic scenes from egocentric audio recordings in workplace setting
• Zero-Shot Audio Classification with Factored Linear and Nonlinear Acoustic-Semantic Projections
• Enhancing Sound Texture in CNN-Based Acoustic Scene Classification
• A Transformer-based Audio Captioning Model with Keyword Estimation
• Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices
• Data-driven audio recognition: a supervised dictionary approach
• DCAR: A Discriminative and Compact Audio Representation to Improve Event Detection
• Robust Acoustic Domain Identification with its Application to Speaker Diarization
• DD-CNN: Depthwise Disout Convolutional Neural Network for Low-complexity Acoustic Scene Classification
• Ensemble Of Deep Neural Networks For Acoustic Scene Classification
• Sub-Spectrogram Segmentation for Environmental Sound Classification via Convolutional Recurrent Neural Network and Score Level Fusion
• Acoustic Scene Classification Using Bilinear Pooling on Time-liked and Frequency-liked Convolution Neural Network