Assessing a domain-adaptive deployment workflow for selective audio recording in wildlife acoustic monitoring

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Azziz, Julia
• dc.contributor.author Lema, Josefina
• dc.contributor.author Anzibar Fialho, Maximiliano
• dc.contributor.author Ziegler, Lucía
• dc.contributor.author Steinfeld, Leonardo
• dc.contributor.author Rocamora, Martín
• dc.date.accessioned 2025-10-13T12:31:18Z
• dc.date.available 2025-10-13T12:31:18Z
• dc.date.issued 2025
• dc.description.abstract Passive acoustic monitoring is a valuable tool for wildlife research, but scheduled recording often results in large volumes of audio, much of which may not be of interest. Selective audio recording, where audio is only saved when relevant activity is detected, offers an effective alternative. In this work, we leverage a low-cost embedded system that implements selective recording using an on-device classification model and evaluate its deployment for detecting penguin vocalizations. To address the domain shift between training and deployment conditions (e.g., environment, recording device), we propose a lightweight domain adaptation strategy based on fine-tuning the model with a small amount of location-specific data. We replicate realistic deployment scenarios using data from two geographically distinct locations, Antarctica and Falkland Islands, and assess the impact of fine-tuning on classification and selective recording performance. Our results show that fine-tuning with location-specific data substantially improves generalization ability and reduces both false positives and false negatives in selective recording. These findings highlight the value of integrating model fine-tuning into field monitoring workflows, in order to improve the reliability of acoustic data collection.
• dc.format.mimetype application/pdf
• dc.identifier.citation Azziz J, Lema J, Anzibar M, Ziegler L, Steinfeld L, Rocamora, M. Assessing a domain-adaptive deployment workflow for selective audio recording in wildlife acoustic monitoring. In: Benetos E, Font F, Fuentes M, Martin Morato I, Rocamora M, editors. Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025); 2025 Oct 30-31; Barcelona, Spain. [Barcelona]: DCASE; 2025. p. 200-4.
• dc.identifier.uri http://hdl.handle.net/10230/71488
• dc.language.iso eng
• dc.publisher Detection and Classification of Acoustic Scenes and Events (DCASE)
• dc.rights This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit: http://creativecommons.org/licenses/by/4.0/
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri http://creativecommons.org/licenses/by/4.0/
• dc.subject.keyword Audio recording
• dc.subject.keyword Wildlife acoustic monitoring
• dc.title Assessing a domain-adaptive deployment workflow for selective audio recording in wildlife acoustic monitoring
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion