• Corpus ID: 219124055

Acoustic Scene Classification in DCASE 2020 Challenge: Generalization Across Devices and Low Complexity Solutions

@inproceedings{Heittola2020AcousticSC,
  title={Acoustic Scene Classification in DCASE 2020 Challenge: Generalization Across Devices and Low Complexity Solutions},
  author={Toni Heittola and Annamaria Mesaros and Tuomas Virtanen},
  booktitle={Workshop on Detection and Classification of Acoustic Scenes and Events},
  year={2020}
}
This paper presents the details of Task 1: Acoustic Scene Classification in the DCASE 2020 Challenge. The task consists of two subtasks: classification of data from multiple devices, requiring good generalization properties, and classification using low-complexity solutions. Here we describe the datasets and baseline systems. After the challenge submission deadline, challenge results and analysis of the submissions will be added. 
[PDF] Semantic Reader
92 Citations
Highly Influential Citations
18
Background Citations
45
Methods Citations
47
Results Citations
2

Figures and Tables from this paper

92 Citations

Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation

This technical report presents a joint effort of four groups, namely GT, USTC, Tencent, and UKE, to tackle Task 1 - Acoustic Scene Classification (ASC) in the DCASE 2020 Challenge, proposing a novel two-stage ASC system leveraging upon ad-hoc score combination of two convolutional neural networks.

LOW-COMPLEXITY ACOUSTIC SCENE CLASSIFICATION WITH SMALL CONVOLUTIONAL NEURAL NETWORKS AND CURRICULUM LEARNING Technical Report

The report presents the results of submission to Task 1B of Detection and Classification of Acoustic Scenes and Events Challenge (DCASE) 2020, where four different models based on convolutional neural networks were developed, varying from data preprocessing methods, data architectures etc.

ACOUSTIC SCENE CLASSIFICATION WITH MULTIPLE DECISION SCHEMES Technical Report

This technical report describes the ADSPLAB team’s submission for Task1 of DCASE2020 challenge, based on the convolutional neural networks, which is the fusion of models with multiple decision schemes and models pre-trained on AudioSet.

CP-JKU SUBMISSIONS TO DCASE’20: LOW-COMPLEXITY CROSS-DEVICE ACOUSTIC SCENE CLASSIFICATION WITH RF-REGULARIZED CNNS Technical Report

This technical report describes the CP-JKU team’s submission for Task 1 – Subtask A (Acoustic Scene Classification with Multiple Devices) and Subtask B (Low-Complexity Acoustic Scene Classification)…

LOW-COMPLEXITY ACOUSTIC SCENE CLASSIFICATION USING PRIMARY AMBIENT EXTRACTION AND CYCLEGAN Technical Report

This report describes our submissions for DCASE2020 Challenge task 1b (Low-Complexity Acoustic Scene Classification). In each submission, constant-Q transform is used as acoustic feature, and the…

Attentive Max Feature Map for Acoustic Scene Classification with Joint Learning considering the Abstraction of Classes

This work proposes a mechanism referred to as the attentivemax feature map which combines two effective techniques, attention and max feature map, to further elaborate the attention mechanism and mitigate the abovementioned phenomenon.

A Two-Stage Approach to Device-Robust Acoustic Scene Classification

  • Hu HuC. Yang Chin-Hui Lee
  • Computer Science
    ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2021
The results show that the proposed ASC system attains a state-of-the-art accuracy on the development set, where the best system, a two-stage fusion of CNN ensembles, delivers a 81.9% average accuracy among multi-device test data, and it obtains a significant improvement on unseen devices.

MEL-SCALED WAVELET-BASED FEATURES FOR SUB-TASK A AND TEXTURE FEATURES FOR SUB-TASK B OF DCASE 2020 TASK 1 Technical Report

The proposed systems outperform the deep-learning based baseline systems with the development dataset provided for the respective sub-tasks.

Acoustic Scene Classification with Spectrogram Processing Strategies

This paper studies the problem of efficiently taking advantage of different spectrogram representations through discriminative processing strategies and proposes the processing strategies in multiple frequency bands and multiple temporal frames to make fully use of a single spectrogram representation.

Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping

A filter-damping technique for regularizing the RF of models, without altering their architecture and changing their parameter counts is proposed, and it is shown that incorporating this technique improves the performance in various low-complexity settings such as pruning and decomposed convolution.
...

24 References

Acoustic Scene Classification: An Overview of Dcase 2017 Challenge Entries

Analysis of the submissions confirms once more the popularity of deep-learning approaches and mel frequency representations in acoustic scene classification, and indicates that combinations of top systems are capable of reaching close to perfect performance on the given data.

Acoustic Scene Classification in DCASE 2019 Challenge: Closed and Open Set Classification and Data Mismatch Setups

The outcome of DCASE 2019 Challenge Task 1 is presented in terms of submitted systems performance and analysis, with top performance being 85.2% for Subtask A, 75.5% forsubtask B, and 67.4% for subtask C.

Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation

This technical report presents a joint effort of four groups, namely GT, USTC, Tencent, and UKE, to tackle Task 1 - Acoustic Scene Classification (ASC) in the DCASE 2020 Challenge, proposing a novel two-stage ASC system leveraging upon ad-hoc score combination of two convolutional neural networks.

Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification

This work proposes a novel approach to learn domain-invariant classifiers in an end-to-end fashion by enforcing equal hidden layer representations for domain-parallel samples, i.e. time-aligned recordings from different recording devices.

Open-Set Acoustic Scene Classification with Deep Convolutional Autoencoders

This paper contains a description of an open-set acoustic scene classification system submitted to task 1C of the Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2019, which consists of a combination of convolutional neural networks for closed-set identification and deep convolved autoencoders for outlier detection.

A multi-device dataset for urban acoustic scene classification

The acoustic scene classification task of DCASE 2018 Challenge and the TUT Urban Acoustic Scenes 2018 dataset provided for the task are introduced, and the performance of a baseline system in the task is evaluated.

Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge

The emergence of deep learning as the most popular classification method is observed, replacing the traditional approaches based on Gaussian mixture models and support vector machines.

Receptive-field-regularized CNN variants for acoustic scene classification

This paper performs a systematic investigation of different RF configuration for various CNN architectures on the DCASE 2019 Task 1.A dataset, introduces Frequency Aware CNNs to compensate for the lack of frequency information caused by the restricted RF, and investigates if and in what RF ranges they yield additional improvement.

SUPERVISED NONNEGATIVE MATRIX FACTORIZATION FOR ACOUSTIC SCENE CLASSIFICATION

The proposed feature learning approach following the idea of decomposing time-frequency representations with nonnegative matrix factorization aims at learning a common dictionary representing the data and use projections on this dictionary as features for classification.

Acoustic scene classification using a convolutional neural network ensemble and nearest neighbor filters

A nearest neighbor filter applied on spectrograms is introduced, which allows to emphasize and smooth similar patterns of sound events in a scene and improve the accuracy of the system significantly.