Classifying Sounds in Polyphonic Urban Sound Scenes

Abeßer J. Classifying Sounds in Polyphonic Urban Sound Scenes. In: AES Convention 152. Audio Engineering Society; 2022. Paper 10570. Available from: https://aes.org/publications/elibrary-page/?id=21683

@inproceedings{Abeser2022_21683,
  author = {Abeßer, Jakob},
  title = {{Classifying Sounds in Polyphonic Urban Sound Scenes}},
  booktitle = {AES Convention 152},
  note = {Paper 10570},
  year = {2022},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=21683}
}

TY  - CPAPER
TI  - Classifying Sounds in Polyphonic Urban Sound Scenes
AU  - Abeßer, Jakob
T2  - AES Convention 152
M1  - Paper 10570
PY  - 2022
DA  - 2022/05/06
UR  - https://aes.org/publications/elibrary-page/?id=21683
PB  - Audio Engineering Society
LA  - en
AB  - The deployment of machine listening algorithms in real-world application scenarios is challenging. In this paper, we investigate how the superposition of multiple sound events within complex sound scenes affects their recognition. As a basis for our research, we introduce the Urban Sound Monitoring (USM) dataset, which is a novel public benchmark dataset for urban sound monitoring tasks. It includes 24,000 sound scenes that are mixed from isolated sounds using different loudness levels, sound polyphony levels, and stereo panorama placements. In a benchmark experiment, we evaluate three deep neural network architectures for sound event tagging (SET) on the USM dataset. In addition to counting the overall number of sounds in a sound scene, we introduce a local sound polyphony measure as well as a temporal and frequency coverage measure of sounds which allow to characterize complex sound scenes. The analysis of these measures confirms that SET performance decreases for higher sound polyphony levels and larger temporal coverage of sounds.
ER  -