Congress and Exposition on Noise Control Engineering

The 53rd International Congress and Exposition on Noise Control Engineering will take place from August25 to29, 2024 in Nantes, France. 

Our audio expert Jakob Abeßer and Sebastian Stober from Otto-von-Guericke-Universität Magdeburg, will organize the technical session "Machine Learning for Acoustic Scene Understanding". The session will specifically present and discuss contributions about environmental audio analysis tasks such as sound event detection and acoustic scene classification as well as practical challenges in acoustic monitoring application scenarios such as industrial audio analysis, urban sound monitoring, and bioacoustic monitoring.

Wednesday, August 28, 2024, Room I

Presenter: Saichand Gourishetti

In industrial extrusion processes, a solid material is pressed through a die to obtain products of the desired shape and dimension. Fluctuations in the process parameters have a significant impact on the product quality. In food extrusion, the expansion noise at the die may serve as an indicator of the stability of the process. This study employs microphones to characterize the corn extrusion process, focusing on correlating acoustic emissions with process parameters such as feed intake and water content. Employing a convolutional neural network with audio features in log Mel spectrograms yields promising accuracies above 90% in discriminating between standard and non-standard process parameters in laboratory and industrial environments. However, a comprehensive dataset and additional pre-processing methods, such as adaptive normalization, are essential to generalize unseen environments. The proposed acoustic quality control approach can potentially enhance the stability of extrusion processes and contribute to the development of automated monitoring systems in food extrusion. This ensures consistent quality and reduced rejects, ultimately leading to significant cost savings in production.

Session 3.4.: Artificial Intelligence and Machine Learning for Diagnosis in Acoustics & Vibration 
Monday, August 26, 2024, Room GH 

Presenter: Saichand Gourishetti

Deep audio representations, also known as embeddings, recently became a popular alternative to conventional features like spectrograms for a wide range of audio classification tasks because of their domain-agnostic character and reduced training costs. Still, the usage is often limited to rather computationally intensive system due to the nature of their extraction from large networks. This paper aims to minimize the computational costs of embedding extraction by distilling the knowledge of the OpenL3 audio network to a smaller student network. Results show that the student network maintains comparable performance as the teacher network on various music and ambient noise classification tasks, while reducing the network size by over 90% and the computational load by five times.

Session 5.0.: Signal Processing, Reproduction & Diagnostics: General
Wednesday, August 28, 2024, Room GH