Conference paper Open Access
Low-Complexity Acoustic Scene Classification in DCASE 2022 Challenge
Irene Martin-Morato; Francesco Paissan; Alberto Ancilotto; Toni Heittola; Annamaria Mesaros; Elisabetta Farella; Alessio Brutti; Tuomas Virtanen
This paper presents an analysis of the Low-Complexity Acoustic Scene Classification task in DCASE 2022 Challenge. The task was a continuation from the previous years, but the low-complexity requirements were changed to the following: the maximum number of allowed parameters, including the zero-valued ones, was 128 K, with parameters being represented using INT8 numerical for- mat; and the maximum number of multiply-accumulate operations at inference time was 30 million. Despite using the same previous year dataset, the audio samples have been shortened to 1 second instead of 10 second for this year challenge. The provided baseline system is a convolutional neural network which employs post-training quantization of parameters, resulting in 46.5 K parameters, and 29.23 million multiply-and-accumulate operations (MMACs). Its performance on the evaluation data is 44.2% accuracy and 1.532 log-loss. In comparison, the top system in the challenge obtained an accuracy of 59.6% and a log loss of 1.091, having 121 K parameters and 28 MMACs. The task received 48 submissions from 19 different teams, most of which outperformed the baseline system.
| Name | Size | |
|---|---|---|
|
Low_complexity_acoustic_scene_classification_in_dcase2022_challenge.pdf
md5:db76c39bf7cc8f4b81db1c59124a8930 |
215.4 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 32 | 32 |
| Downloads | 28 | 28 |
| Data volume | 6.0 MB | 6.0 MB |
| Unique views | 25 | 25 |
| Unique downloads | 24 | 24 |
- Publication date:
- December 7, 2022
- DOI:
-
- Keyword(s):
- Acoustic scene classification low-complexity DCASE Challenge
- Grants:
-
European Commission:
- MARVEL - Multimodal Extreme Scale Data Analytics for Smart Cities Environments (957337)
- Meeting:
- 7th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2022), Nancy, France, 3 November 2022
- Related identifiers:
- Published in
- Supplementary material
- https://github.com/marmoi/dcase2022_task1_baseline (Software)
- 10.5281/zenodo.6337421 (Dataset)
- 10.5281/zenodo.6591203 (Dataset)
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International