ishine/dcase2020_task1

Code for DCASE 2020 task 1a and task 1b.

DCASE2020 Task1

Task1a | Task1b | Video | dcase paper | icassp paper | |

New We add a list on recent related ASC works containing discussion with this open resource ASC studies. Welcome to open an issue for adding related reference with the open resouce studies or just sharing your work.

This work has been accepted to IEEE ICASSP 2021! (Session Time: Friday, 11 June, 13:00 - 13:45 presented by Hu Hu)

Introduction

This is an implementation of DCASE 2020 Task 1a and DCASE 2020 Task 1b on Acoustic Scene Classification with Multiple Devices. We attain 2nds for both Task-1a and Task-1b in the official challenge 2020. Technical Report.

We sincerely thank all the team members and advisors from Georgia Tech ECE, Tencent Media Lab, USTC, and Univeristy of Enna.

Experimental results

Task 1a

Tested on DCASE 2020 task 1a development data set. The train-test split way follows the official recomendation.

System	Dev Acc.
Official Baseline	51.4%
10-class FCNN	76.9%
10-class Resnet	74.6%
10-class fsFCNN	76.2%
Two-stage ensemble system	81.9%

Task 1b

Tested on DCASE 2020 task 1b development data set. The train-test split way follows the official recomendation.

System	Dev Acc. (size) Original model	Dev Acc. (size) Quantization
Official Baseline	87.3% (450K)	-
Mobnet	95.2% (3.2M)	94.8% (411K)
small-FCNN	96.4% (2.8M)	96.3% (357K)
Mobnet + small-FCNN-v1	96.8% (1.8M+1.9M)	96.7% (497K)
small-FCNN-v1 + small-FCNN-v2	96.5% (1.9M+2.1M)	96.3% (499K)

How to use

Task 1a

Please refer to the README.md in ./task1a/ for detailed instructions.

Task 1b

Please refer to the README.md in ./task1b/ for detailed instructions.

Pre-trained models

• Pre-trained keras models are provided in ./task1a/3class/pretrained_models/, task1a/10class/pretrained_models/, and ./task1b/pretrained_models/. You can get reported results by directly evaluate pre-trained models.

• tensorflow >= 2.0 pretrained models. We also provide some pretrained DCASE task1 models in tensorflow >= 2.0 format. Please refer to ./other_TF2_format_pretrained/

Reference

If this work helps or has been used in your research, please consider to cite both papers below. Thank you!

@inproceedings{hu2021two,
  title={A two-stage approach to device-robust acoustic scene classification},
  author={Hu, Hu and Yang, Chao-Han Huck and Xia, Xianjun and Bai, Xue and Tang, Xin and Wang, Yajian and Niu, Shutong and Chai, Li and Li, Juanjuan and Zhu, Hongning and others},
  booktitle={ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={845--849},
  year={2021},
  organization={IEEE}
}


@misc{hu2020devicerobust,
    title={Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation},
    author={Hu Hu and Chao-Han Huck Yang and Xianjun Xia and Xue Bai and Xin Tang and Yajian Wang and Shutong Niu and Li Chai and Juanjuan Li and Hongning Zhu and Feng Bao and Yuanjun Zhao and Sabato Marco Siniscalchi and Yannan Wang and Jun Du and Chin-Hui Lee},
    year={2020},
    eprint={2007.08389},
    archivePrefix={arXiv},
    primaryClass={eess.AS}
}

More Recent Related Works

Noted We simply generated the lists from reference tools. Feel free to pin us if you would like to share your work here.

• Related to Hu et al. "A Two-Stage Approach to Device-Robust Acoustic Scene Classification." ICASSP (2021).

Title	Authors & Paper Link	Proc.
Attentive Max Feature Map for Acoustic Scene Classification with Joint Learning considering the Abstraction of Classes	Shim, H., et al.	Arxiv 2021
Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification	D. Yang, et al.	Arxiv 2021
CLOVA SUBMISSION FOR THE DCASE 2021 CHALLENGE: ACOUSTIC SCENECLASSIFICATION USING LIGHT ARCHITECTURES AND DEVICE AUGMENTATION	Heo H., et al.	DCASE 2021
A Multi-Head Relevance Weighting Framework For Learning Raw Waveform Audio Representations	D Dutta et al.	WASPAA 21
A MODEL ENSEMBLE APPROACH FOR AUDIO-VISUAL SCENE CLASSIFICATION	Q. Wang, et al.	DCASE 2021

• Related to Hu, et al. "Device-robust acoustic scene classification based on two-stage categorization and data augmentation." DCASE (2020).

Title	Authors & Paper Link	Proc.
Multi-Scale Temporal Convolution Network for Classroom Voice Detection	L Ma, et al.	Arxiv 2021
Acoustic scene classification in dcase 2020 challenge: generalization across devices and low complexity solutions	T Heittola, et al.	DCASE 2020
CNN-Based Acoustic Scene Classification System	Y Lee t al.	Electronics 2021
Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification	Hu et al.	Arxiv 2020
Attentive Max Feature Map for Acoustic Scene Classification with Joint Learning considering the Abstraction of Classes	H Shim et al.	Arxiv 2021
A Two-Stage Approach to Device-Robust Acoustic Scene Classification	Hu et al.	ICASSP 2021
Slow-Fast Auditory Streams for Audio Recognition	E Kazakos et al.	ICASSP 2021
Accelerating On-Device Learning with Layer-Wise Processor Selection Method on Unified Memory	Ha, D. et al.	Sensors 2021
Attentive Max Feature Map for Acoustic Scene Classification with Joint Learning considering the Abstraction of Classes	Shim, H., et al.	Arxiv 2021
Cross-Modal Spectrum Transformation Network for Acoustic Scene Classification	Y. Liu et al.	ICASSP 2021
A Multi-Head Relevance Weighting Framework For Learning Raw Waveform Audio Representations	D Dutta et al.	WASPAA 21
Shallow Convolution-Augmented Transformer with Differentiable Neural Computer for Low-Complexity Classification of Variable-Length Acoustic Scene	S. Seo et al.	Interspeech 21
Robust Acoustic Scene Classification in the Presence of Active Foreground Speech	S. Song et al.	Arxiv 21

Acknowledgements

Codes borrows heavily from DCASE2019-Task1 and dcase2020_task1_baseline. We appreciate the researchers contributing to this ASC community.