From acoustic scene to sense of place: Sound scene-to-description, a semantic translation engine for sound environment
The Journal of the Acoustical Society of America · 2026
DOI: 10.1121/10.0046521 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, 2026. Verfasst von Yonggai Zhuang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Resource and Environmental Sciences, Wuhan University, Wuhan, China. Hauptthemen laut MEDLINE: Sound, Acoustics, Semantics, Auditory Perception. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Open Fund of the State Key Laboratory of Resources and Environmental Information Systems.
Abstract (Originalsprache)
Sound environments play a crucial role in human experience, shaping memory, comfort, and sense of place. They provide essential cues for judging safety and atmosphere in both real and virtual settings. Despite the growing availability of large audio libraries, extracting meaningful information from complex and overlapping sound scenes remains difficult. Audio captioning addresses this challenge by translating acoustic scenes into text, yet traditional approaches face clear limitations. Manual annotation is often subjective and incomplete, while sound event detection reduces audio to isolated tags without capturing context, relationships, or temporal dynamics. To overcome these barriers, this study proposes sound scene-to-description (SS2D), a method that trains an audio encoder to map complex sound patterns into the semantic space of a large language model. This allows the model to generate coherent and detailed descriptions that reflect interactions among sounds and their evolution over time, moving beyond simple event lists. In both qualitative and quantitative evaluations, SS2D has demonstrated significantly better performance than the audio event method and the image caption method. In terms of practical significance, SS2D eliminates the need for extensive manual labeling and has broad applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Resource and Environmental Sciences, Wuhan University, Wuhan, China.
- Beijing Institute of Technology (Zhuhai), Zhuhai, China.
- University of Canterbury, Christchurch, New Zealand.
- State Key Laboratory of Resources and Environmental Information System, Beijing, China.
- Information Center of Natural Resources, Department of Natural Resources of Ningxia Hui Autonomous Region, Yinjiaqu North Street 25, Ningxia 750004, China.
Förderung
- National Natural Science Foundation of China
- National Key R&D Program of China
- Open Fund of the State Key Laboratory of Resources and Environmental Information Systems
Zitieren
APA
Zhuang, Y., Fei, T., Du, Y., & Liu, D. (2026). From acoustic scene to sense of place: Sound scene-to-description, a semantic translation engine for sound environment. The Journal of the Acoustical Society of America. https://doi.org/10.1121/10.0046521
Vancouver
Zhuang Y, Fei T, Du Y, Liu D. From acoustic scene to sense of place: Sound scene-to-description, a semantic translation engine for sound environment. The Journal of the Acoustical Society of America. 2026. doi:10.1121/10.0046521
BibTeX
@article{Zhuang2026,
author = {Zhuang, Yonggai and Fei, Teng and Du, Yunyan and Liu, Dan},
title = {From acoustic scene to sense of place: Sound scene-to-description, a semantic translation engine for sound environment},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
doi = {10.1121/10.0046521}
}
EUVIMED