Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge

Florian Schmid; Paul Primus; I. Martín-Morató; T. Heittola; Gerhard Widmer; A. Mesaros

Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge

Florian Schmid
, Paul Primus
, I. Martín-Morató
, T. Heittola
, Gerhard Widmer
, A. Mesaros

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

This paper presents the Low-Complexity Acoustic Scene Classification with Device Information Task of the DCASE 2025 Challenge and its baseline system. Continuing the focus on low-complexity models, data efficiency, and device mismatch from previous editions (2022--2024), this year's task introduces a key change: recording device information is now provided at inference time. This enables the development of device-specific models that leverage device characteristics -- reflecting real-world deployment scenarios in which a model is designed with awareness of the underlying hardware. The training set matches the 25% subset used in the corresponding DCASE 2024 challenge, with no restrictions on external data use, highlighting transfer learning as a central topic. The baseline achieves 50.72% accuracy on this ten-class problem with a device-general model, improving to 51.89% when using the available device information.

Original language	English
Title of host publication	Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025)
Edition	1
Publication status	Published - 2025

Fields of science

102003 Image processing
202002 Audiovisual media
102001 Artificial intelligence
102015 Information systems
102 Computer Sciences
101019 Stochastics
103029 Statistical physics
101018 Statistics
101017 Game theory
202017 Embedded systems
101016 Optimisation
101015 Operations research
101014 Numerical mathematics
101029 Mathematical statistics
101028 Mathematical modelling
101026 Time series analysis
101024 Probability theory
102032 Computational intelligence
102004 Bioinformatics
102013 Human-computer interaction
101027 Dynamical systems
305907 Medical statistics
101004 Biomathematics
305905 Medical informatics
101031 Approximation theory
102033 Data mining
305901 Computer-aided diagnosis and therapy
102019 Machine learning
106007 Biostatistics
102018 Artificial neural networks
106005 Bioinformatics
202037 Signal processing
202036 Sensor systems
202035 Robotics

JKU Focus areas

Digital Transformation

Access to Document

https://dcase.community/challenge2025/task-low-complexity-acoustic-scene-classification-with-device-information

Cite this

Schmid, F., Primus, P., Martín-Morató, I., Heittola, T., Widmer, G., & Mesaros, A. (2025). Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge. In Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025) (1 ed.) https://dcase.community/challenge2025/task-low-complexity-acoustic-scene-classification-with-device-information

@inproceedings{0e6d24cad77f43c18caae2146e768844,

title = "Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge",

abstract = " This paper presents the Low-Complexity Acoustic Scene Classification with Device Information Task of the DCASE 2025 Challenge and its baseline system. Continuing the focus on low-complexity models, data efficiency, and device mismatch from previous editions (2022--2024), this year's task introduces a key change: recording device information is now provided at inference time. This enables the development of device-specific models that leverage device characteristics -- reflecting real-world deployment scenarios in which a model is designed with awareness of the underlying hardware. The training set matches the 25\% subset used in the corresponding DCASE 2024 challenge, with no restrictions on external data use, highlighting transfer learning as a central topic. The baseline achieves 50.72\% accuracy on this ten-class problem with a device-general model, improving to 51.89\% when using the available device information. ",

author = "Florian Schmid and Paul Primus and I. Mart{\'i}n-Morat{\'o} and T. Heittola and Gerhard Widmer and A. Mesaros",

year = "2025",

language = "English",

booktitle = "Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025)",

edition = "1",

}

Schmid, F , Primus, P, Martín-Morató, I, Heittola, T, Widmer, G & Mesaros, A 2025, Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge. in Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025). 1 edn. <https://dcase.community/challenge2025/task-low-complexity-acoustic-scene-classification-with-device-information>

Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge. / Schmid, Florian ; Primus, Paul; Martín-Morató, I. et al.
Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025). 1. ed. 2025.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

TY - GEN

T1 - Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge

AU - Schmid, Florian

AU - Primus, Paul

AU - Martín-Morató, I.

AU - Heittola, T.

AU - Widmer, Gerhard

AU - Mesaros, A.

PY - 2025

Y1 - 2025

N2 - This paper presents the Low-Complexity Acoustic Scene Classification with Device Information Task of the DCASE 2025 Challenge and its baseline system. Continuing the focus on low-complexity models, data efficiency, and device mismatch from previous editions (2022--2024), this year's task introduces a key change: recording device information is now provided at inference time. This enables the development of device-specific models that leverage device characteristics -- reflecting real-world deployment scenarios in which a model is designed with awareness of the underlying hardware. The training set matches the 25% subset used in the corresponding DCASE 2024 challenge, with no restrictions on external data use, highlighting transfer learning as a central topic. The baseline achieves 50.72% accuracy on this ten-class problem with a device-general model, improving to 51.89% when using the available device information.

AB - This paper presents the Low-Complexity Acoustic Scene Classification with Device Information Task of the DCASE 2025 Challenge and its baseline system. Continuing the focus on low-complexity models, data efficiency, and device mismatch from previous editions (2022--2024), this year's task introduces a key change: recording device information is now provided at inference time. This enables the development of device-specific models that leverage device characteristics -- reflecting real-world deployment scenarios in which a model is designed with awareness of the underlying hardware. The training set matches the 25% subset used in the corresponding DCASE 2024 challenge, with no restrictions on external data use, highlighting transfer learning as a central topic. The baseline achieves 50.72% accuracy on this ten-class problem with a device-general model, improving to 51.89% when using the available device information.

M3 - Conference proceedings

BT - Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025)

ER -