AI-based soundscape analysis: Jointly identifying sound sources and predicting annoyance
The Journal of the Acoustical Society of America · 01.11.2023 · 154 (5) · 3145-3157
DOI: 10.1121/10.0022408 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 15.11.2023. Verfasst von Yuanbo Hou und 6 weiteren Autor:innen. Beteiligte Einrichtung: Wireless, Acoustics, Environmental, and Expert Systems Research Group, Department of Information Technology, Ghent University, Gent, 9052, Belgium. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Flemish Government.
Abstract (Originalsprache)
Soundscape studies typically attempt to capture the perception and understanding of sonic environments by surveying users. However, for long-term monitoring or assessing interventions, sound-signal-based approaches are required. To this end, most previous research focused on psycho-acoustic quantities or automatic sound recognition. Few attempts were made to include appraisal (e.g., in circumplex frameworks). This paper proposes an artificial intelligence (AI)-based dual-branch convolutional neural network with cross-attention-based fusion (DCNN-CaF) to analyze automatic soundscape characterization, including sound recognition and appraisal. Using the DeLTA dataset containing human-annotated sound source labels and perceived annoyance, the DCNN-CaF is proposed to perform sound source classification (SSC) and human-perceived annoyance rating prediction (ARP). Experimental findings indicate that (1) the proposed DCNN-CaF using loudness and Mel features outperforms the DCNN-CaF using only one of them. (2) The proposed DCNN-CaF with cross-attention fusion outperforms other typical AI-based models and soundscape-related traditional machine learning methods on the SSC and ARP tasks. (3) Correlation analysis reveals that the relationship between sound sources and annoyance is similar for humans and the proposed AI-based DCNN-CaF model. (4) Generalization tests show that the proposed model's ARP in the presence of model-unknown sound sources is consistent with expert expectations and can explain previous findings from the literature on soundscape augmentation.
Autor:innen und Institutionen
- Wireless, Acoustics, Environmental, and Expert Systems Research Group, Department of Information Technology, Ghent University, Gent, 9052, Belgium.
- AI and Robotics, Internet Technology and Data Science Lab, Department of Electronics and Information Systems, Interuniversity Microelectronics Centre, Ghent University, Gent, 9052, Belgium.
- Institute for Environmental Design and Engineering, The Bartlett, University College London, London, WC1H 0NN, United Kingdom.
ORCID-Profile: Yuanbo Hou, Qiaoqiao Ren, Andrew Mitchell, Francesco Aletta, Jian Kang
Förderung
- Flemish Government
Zitieren
APA
Hou, Y., Ren, Q., Zhang, H., Mitchell, A., Aletta, F., Kang, J., & Botteldooren, D. (2023). AI-based soundscape analysis: Jointly identifying sound sources and predicting annoyance. The Journal of the Acoustical Society of America, 154(5), 3145-3157. https://doi.org/10.1121/10.0022408
Vancouver
Hou Y, Ren Q, Zhang H, Mitchell A, Aletta F, Kang J, et al. AI-based soundscape analysis: Jointly identifying sound sources and predicting annoyance. The Journal of the Acoustical Society of America. 2023;154(5):3145-3157. doi:10.1121/10.0022408
BibTeX
@article{Hou2023,
author = {Hou, Yuanbo and Ren, Qiaoqiao and Zhang, Huizhong and Mitchell, Andrew and Aletta, Francesco and Kang, Jian and Botteldooren, Dick},
title = {AI-based soundscape analysis: Jointly identifying sound sources and predicting annoyance},
journal = {The Journal of the Acoustical Society of America},
year = {2023},
volume = {154},
number = {5},
pages = {3145--3157},
doi = {10.1121/10.0022408}
}
EUVIMED