Published March 15, 2024 | Version v1
Dataset Open

IEEE ICME 2024 Grand Challenge: Semi-supervised Acoustic Scene Classification under Domain Shift Evaluation Dataset

  • 1. ROR icon Northwestern Polytechnical University
  • 2. Xi'an Lianfeng Acoustic Technologies Co., Ltd.
  • 3. Institute of Acoustics, Chinese Academy of Sciences
  • 4. ROR icon University of Surrey
  • 5. ROR icon Nanyang Technological University

Description

The Chinese Acoustic Scene (CAS) 2023 dataset is a large-scale dataset that serves as a foundation for research related to environmental acoustic scenes. The dataset includes 10 common acoustic scenes, with a total duration of over 130 hours. Each audio clip is 10 seconds long with metadata about the recording location and timestamp. The dataset was collected by members of the Joint Laboratory of Environmental Sound Sensing at the School of Marine Science and Technology, Northwestern Polytechnical University. The data collection period spanned from April 2023 to September 2023, covering 22 different cities across China. The CAS 2023 dataset was collected using the XS-SN-2BE1 manufactured by Xi'an Lianfeng Acoustic Technologies Co., Ltd (https://www.lfxstek.com/).  

The ICME 2024 Semi-supervised Acoustic Scene Classification under Domain Shift challenge (https://2024.ieeeicme.org/grand-challenge-proposals/, https://ascchallenge.xshengyun.com/) dataset consists of development (https://zenodo.org/records/10616533) and evaluation datasets, all derived from the CAS 2023 dataset. The evaluation dataset includes 1,100 recordings, where data are selected from 12 cities, with 5 unseen cities specifically chosen to provide a more comprehensive evaluation of submissions under domain shift.

Baseline: https://github.com/JishengBai/ICME2024ASC

Acoustic scenes (10): Bus, Airport, Metro, Restaurant, Shopping mall, Public square, Urban park, Traffic street, Construction site, Bar

Files

ICME2024_ASC_eval.csv

Files (671.8 MB)

Name Size Download all
md5:0f87c888b4b813af71499c1d506f9b1a
42.8 kB Preview Download
md5:b05ca3f94743e167d812d4ed70659e30
671.8 MB Preview Download

Additional details

References

  • Bai, Jisheng, et al. "Description on IEEE ICME 2024 Grand Challenge: Semi-supervised Acoustic Scene Classification under Domain Shift." arXiv preprint arXiv:2402.02694 (2024).