Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Enhancing Multiscale Features for Efficient Acoustic Scene Classification with One-Dimensional Separate CNN

Publikation

Enhancing Multiscale Features for Efficient Acoustic Scene Classification with One-Dimensional Separate CNN

He, Yuxuan; Raake, Alexander; Abeßer, Jakob (2026): Enhancing Multiscale Features for Efficient Acoustic Scene Classification with One-Dimensional Separate CNN, in: Bamberg: Otto-Friedrich-Universität, S. 125–129.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
He, Yuxuan
Raake, Alexander
Verlagsangabe
Otto-Friedrich-Universität : Bamberg
Erscheinungsjahr
2026
Quelle/Weitere Ausgabe
Emmanouil Benetos, Frederic Font, Magdalena Fuentes, u. a. (Hrsg.), Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025), October 2025, Zenodo, 2025, S. 125–129, ISBN: 978-84-09-77652-8
Jahr der Erstpublikation
2025
Sprache(n)
Englisch
Lizenz
URN
Abstract

Acoustic Scene Classifcation (ASC) is a fundamental task in audio signal processing, aiming to classify the location of an environmental audio recording. Recent advances focus on improving ASC model effciency, particularly in resource-constrained environments. Convolutional neural networks (CNNs) remain the dominant approach due to their high performance, with recent focus on 1D kernels, such as in the Time-Frequency Separate Network (TFSepNet), for reducing model complexity and computational cost. However,TFSepNet performs feature extraction using a fixed receptive field in both time and frequency dimensions, which restrictsits ability to capture multiscale contextual patterns. In this study, we investigate the integration of multiscale feature extraction modules into TF-SepNet, with the aim of improving model effciency by balancing accuracy and complexity. We propose three architectures, TFSepDCD-Net, TFSepSPP-Net, andTFSepASPP-Net, each with two architectural variants based on TF-SepNet: one replaces its max pooling layers, and the other replaces its final convolutional layer. Each architecture has three confgurations corresponding to different model sizes - small, medium, and large - to explore the tradeoff between accuracy and model complexity. Our experiments show that in corporating multiscale modules allows smaller models to achieve comparable or even superior accuracy to larger baselines. These fndings highlight the potential of multiscale representations for improving the effciency of CNN-based ASC systems, especially in 1D separate architectures like TF-SepNet.

Freie Schlagwort(e)
acoustic scene classifcation
time-frequency separate network
1D kernels
multiscale feature extraction
Peer Reviewed
ja
Internationale Verbreitung
ja
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
02.02.2026

Permalink: https://fis.uni-bamberg.de/handle/uniba/112891 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 16.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.