aiqbench analysis
This research investigates domain adaptation strategies for acoustic scene classification, specifically analyzing how DANN and CDAN techniques perform across different CNN and transformer feature representations on multiple devices. The findings highlight a critical nuance in deploying AI models where adaptation methods must be carefully tailored to the underlying architecture rather than applied uniformly. This work is relevant to practitioners building robust audio recognition systems that maintain performance despite hardware or environmental shifts.
Device Invariance using Domain Adaptation on Acoustic Scene Classification
arXiv:2607.25887v1 Announce Type: cross Abstract: This paper explores the effectiveness of domain adaptation techniques when using convolutional neural network (CNN)-based and transformer-based feature representations for acoustic scene classification. Two well-known domain adaptation techniques, namely domain adversarial neural network (also called DANN) and conditional domain adversarial network (also called CDAN) are evaluated under various domain shifts. Our study indicates that DANN provides effective domain adaptation fairly consistently for both feature extractors. On the other hand, CDAN provides effective domain adaptation only for CNN-based feature extractors. The study gives insights into how domain adaptation methods may need to be tailored to the underlying feature representation. Experimental evaluation with multiple devices on the DCASE 2020 dataset supports the observations.
Abstract:This paper explores the effectiveness of domain adaptation techniques when using convolutional neural network (CNN)-based and transformer-based feature representations for acoustic scene classification. Two well-known domain adaptation techniques, namely domain adversarial neural network (also called DANN) and conditional domain adversarial network (also called CDAN) are evaluated under various domain shifts. Our study indicates that DANN provides effective domain adaptation fairly consistently for both feature extractors. On the other hand, CDAN provides effective domain adaptation only for CNN-based feature extractors. The study gives insights into how domain adaptation methods may need to be tailored to the underlying feature representation. Experimental evaluation with multiple devices on the DCASE 2020 dataset supports the observations.
Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Sound (cs.SD)
arXiv:2607.25887 [eess.AS]
(or arXiv:2607.25887v1 [eess.AS] for this version)
https://doi.org/10.48550/arXiv.2607.25887 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 212 words
Related coverage
Parameter isolation with domain-specific experts for incremental audio classification
arXiv · Sep 15, 2026
[AINews] not much happened today
Latent Space · Sep 18, 2026
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · Sep 24, 2026
ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection
arXiv · Sep 5, 2026