EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Blind Device-Response Interpolation for Intermediate-Domain Unsupervised Adaptation in Cross-Device Acoustic Scene Classification

Claire Whitmore, Lucas Bennett

Academic Journal of Applied Sciences · 2026

DOI: 10.54097/1ygj4b05 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Journal of Applied Sciences, 2026. Verfasst von Claire Whitmore und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recording-device mismatch is one of the dominant failure modes of acoustic scene classification: a model trained on one microphone degrades sharply on an unseen one. Aligning source and target in a single adversarial step is unstable when the device gap is large, and recent intermediate-domain formulations mitigate this by inserting bridge domains, but they build those bridges from hand-specified parametric device operators that are unavailable at deployment time. We propose BRIDA, an intermediate-domain unsupervised adaptation framework whose bridges are derived from the device response itself. A blind estimator recovers the relative log-mel magnitude response between the labelled source devices and the unlabelled target device from long-term spectral statistics alone, with an optional class-balanced refinement for the case where the two unlabelled pools differ in scene composition. Because a magnitude filter is additive in the log-mel domain, fractional powers of the estimate yield a continuum of label-preserving bridge domains at essentially zero cost; we traverse that continuum with a curriculum and regularise it with an ordinal path-position adversary, a residual maximum-mean-discrepancy anchor and confidence-gated target prototypes. Experiments use 1648 real recordings and 66 measured microphone impulse responses under a leave-one-device-out protocol with disjoint source, target and evaluation content. Averaged over 3 unseen devices and 3 seeds, BRIDA attains 53.00 ± 4.29% target accuracy and 52.99 ± 4.58% macro-F1, improving on source-only training by 7.83 points and on a discrete two-bridge intermediate-domain baseline by 0.61 points, with no inference-time overhead.

Zitieren

APA

Whitmore, C., & Bennett, L. (2026). Blind Device-Response Interpolation for Intermediate-Domain Unsupervised Adaptation in Cross-Device Acoustic Scene Classification. Academic Journal of Applied Sciences. https://doi.org/10.54097/1ygj4b05

Vancouver

Whitmore C, Bennett L. Blind Device-Response Interpolation for Intermediate-Domain Unsupervised Adaptation in Cross-Device Acoustic Scene Classification. Academic Journal of Applied Sciences. 2026. doi:10.54097/1ygj4b05

BibTeX
@article{Whitmore2026,
  author = {Whitmore, Claire and Bennett, Lucas},
  title = {Blind Device-Response Interpolation for Intermediate-Domain Unsupervised Adaptation in Cross-Device Acoustic Scene Classification},
  journal = {Academic Journal of Applied Sciences},
  year = {2026},
  doi = {10.54097/1ygj4b05}
}
Kostenlos starten →