TY - GEN

T1 - CNN-based multi-class multi-label classification of sound scenes in the context of wind turbine sound emission measurements

AU - Poschadel, Nils

AU - Gill, Christian

AU - Preihs, Stephan

AU - Peissig, Jürgen

N1 - Funding Information: The work described in this publication was part of the project WEA-Akzeptanz (FKZ 0324134A) which was funded by the German Federal Ministry for Economic Affairs and Energy (BMWi). We thank the BMWi for the funding we received and the Institute of Structural Analysis (Leibniz University Hannover) for the fruitful collaboration.

PY - 2021/8/1

Y1 - 2021/8/1

N2 - Within the scope of the interdisciplinary project WEA-Akzeptanz, measurements of the sound emission of wind turbines were carried out at the Leibniz University Hannover. Due to the environment there are interfering components (e. g. traffic, birdsong, wind, rain,...) in the recorded signals. Depending on the subsequent signal processing and analysis, it may be necessary to identify sections with the raw sound of a wind turbine, recordings with the purest possible background noise or even a specific combination of interfering noises. Due to the amount of data, a manual classification of the audio signals is usually not feasible and an automated classification becomes necessary. In this paper, we extend our previously proposed multi-class single-label classification model to a multi-class multi-label model, which reflects the real-world acoustic conditions around wind turbines more accurately and allows for finer-grained evaluations. We first provide a short overview of the data acquisition and the dataset. We then briefly summarize our previous approach, extend it to a multi-class multi-label formulation, and analyze the trained convolutional neural network regarding different metrics. All in all, the model delivers very reliable classification results with an overall example-based F1-score of about 79 % for a multi-label classification of 12 classes.

AB - Within the scope of the interdisciplinary project WEA-Akzeptanz, measurements of the sound emission of wind turbines were carried out at the Leibniz University Hannover. Due to the environment there are interfering components (e. g. traffic, birdsong, wind, rain,...) in the recorded signals. Depending on the subsequent signal processing and analysis, it may be necessary to identify sections with the raw sound of a wind turbine, recordings with the purest possible background noise or even a specific combination of interfering noises. Due to the amount of data, a manual classification of the audio signals is usually not feasible and an automated classification becomes necessary. In this paper, we extend our previously proposed multi-class single-label classification model to a multi-class multi-label model, which reflects the real-world acoustic conditions around wind turbines more accurately and allows for finer-grained evaluations. We first provide a short overview of the data acquisition and the dataset. We then briefly summarize our previous approach, extend it to a multi-class multi-label formulation, and analyze the trained convolutional neural network regarding different metrics. All in all, the model delivers very reliable classification results with an overall example-based F1-score of about 79 % for a multi-label classification of 12 classes.

UR - http://www.scopus.com/inward/record.url?scp=85117408837&partnerID=8YFLogxK

U2 - 10.3397/IN-2021-2205

DO - 10.3397/IN-2021-2205

M3 - Conference contribution

AN - SCOPUS:85117408837

T3 - Proceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering

SP - 2687

EP - 2698

BT - Proceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering

A2 - Dare, Tyler

A2 - Bolton, Stuart

A2 - Davies, Patricia

A2 - Xue, Yutong

A2 - Ebbitt, Gordon

T2 - 50th International Congress and Exposition of Noise Control Engineering, INTER-NOISE 2021

Y2 - 1 August 2021 through 5 August 2021

ER -