DAS I DAGA 2025 - Fraunhofer IDMT

Copenhagen / March 17, 2025 - March 20, 2025

DAS I DAGA 2025 – 51. Annual Meeting on Acoustics

The Fraunhofer IDMT is participating in DAS I DAGA 2025, the first joint annual conference of the German Acoustical Society (DEGA) and the Danish Acoustical Society (DAS), as an exhibitor and with several technical contributions.

At the Ilmenau Fraunhofer IDMT stand visitors can find out about current research activities in the field of intelligent acoustic sensors and the analysis of industrial and environmental noise. Visit us at stand B4-34, find out about current developments and exchange ideas with our scientists.

Contributions of the Fraunhofer IDMT to DAGA 2025

on the topics of sound field control, intelligent acoustic sensors, analysis of industrial and environmental sound, as well as speech intelligibility, speech perception and voice control

Session »Hearing Acoustics«

Real-time assessment of listening effort using non-intrusive binaural prediction models

Speaker: Jan Rennies-Hochmuth
Oral presentation I March 17, 2025 I 3.40 p.m. I room 20

view abstract

Session »Bioacoustics«

Analysing Bowel Sound Signals: Insights from SonicGuard Data Collection

Speaker: Danilo Hollosi
Poster presentation I March 18, 2025 I 03.20 p.m. I Nordhavn (B3M10)

view abstract

Session »Noise at the Work Place«

Individual Case or a More General Problem? Investigating Altered Localization Cues with Different Level-Dependent Hearing Protection Devices Concerning Worker Safety

Speaker: Sina Buchholz
Oral presentation I March 19, 2025 I 11.00 a.m. I Nordhavn (B3M10)

view abstract

Session »Acoustic Scene Analysis using Artificial Intelligence«

Extension of the auditory information in time-frequency representations of audio signals for machine learning applications

Speaker: Draško Mašović
Oral presentation I March 19, 2025 I 2.20 p.m. I room 20

view abstract

Session »Acoustic Scene Analysis using Artificial Intelligence«

Semi-supervised Learning for Acoustic Scene Classification using FixMatch

Speaker: Jakob Abeßer
Oral presentation I March 19, 2025 I 2.40 p.m. I room 20

view abstract

Session »Acoustic Scene Analysis using Artificial Intelligence«

Bridging The Gap: GANs As A Solution For Data-Scarce Industrial Audio Classification

Speaker: Pitchapa Ngamthipwatthana
Poster presentation I March 19, 2025 I 3.20 a.m. I room 20

view abstract

Session »Electroacoustics and Audio Signal Processing«

Investigation of Electroacoustic Properties of Experimental Fibre-Optic Microphone Designs

Speaker: Florian Klein
Oral presentation I March 20, 2025 I 9.00 a.m. I Vesterbro (B3M2)

view abstract

Session »Soundscape«

Variance-maximizing acoustic dimensions for machine learning-based soundscape assessment

Speaker: Jakob Bergner
Oral presentation I March 20, 2025 I 10.40 a.m. I Sydhavn (B4M4)

view abstract

Session »Electroacoustics and Audio Signal Processing«

Modeling of Microchannel Acoustics: Relevant Phenomena and Acoustic Impedance Models

Speaker: Andreas Männchen
Poster presentation I March 20, 2025 I 11.00 a.m. I Vesterbro (B3M2)

view abstract

Session »Speech Processing«

Multilingual Listening Effort Prediction - LEAP goes international

Speaker: Rainer Huber
Poster presentation I March 20, 2025 I 11.00 a.m. I room 19

view abstract

Session »Acoustic Measurements and Sensor Technology«

MPEG Audio Coding for Machines

Speaker: Thomas Sporer
Oral presentation I March 20, 2025 I 3.40 p.m. I Østerbro (B3M6)

view abstract

Session tba

How does training impact distance perception of warning signals?

Speaker: Carolin Schnetzer

Poster presentation I tba

Structured Session "Sound Analysis for Music and Audio Signals"

Our expert Jakob Abeßer and Toni Heittola (University of Tampere, Finland) are organising the structured session ‘"Acoustic Scene Analysis using Artificial Intelligence".

The session explores key research directions in acoustic scene classification, sound event detection and sound event localization and detection to enhance model performance and address existing challenges related to

Robustness to Device or Location Mismatch: Ensuring analysis systems perform well across varying recording devices or locations is crucial for applications like context-aware hearing aids or mobile phones. The focus is on models that generalize effectively in dynamic environments.
Data Scarcity: Handling limited or imbalanced training data is a major challenge. Techniques to improve performance with minimal data are being explored to develop more resilient analysis systems
Relation Between Acoustic Scene Classification and Sound Event Detection: Investigating how specific sound events and their temporal patterns characterize acoustic scenes helps refine acoustic scene classification models, improving classification accuracy and how acoustic scene information can improve sound event detection process.
Efficient Neural Network Structures: Techniques like pruning, model distillation, and student-teacher learning are being applied to create lightweight, efficient models for resource-constrained devices.
Cross-disciplinary Insights: Acoustic scene analysis's relationship to auditory scene analysis, room acoustics, and VR/AR highlights its broader applications, aiming for more accurate and immersive classification systems.

Further contributions to DAGA 2025 in which the Fraunhofer IDMT is involved

Analysis of Room Acoustic Measurements Indoors, Outdoors and In Between
Speaker: Paul Popp (TU Ilmenau)
Poster presentation I March 18, 2025 I 3.20 p.m. I room 3

Using interaural mistuning for modelling binaural processing inaccuracies in human speech recognition
Speaker: Simon Weihe (CvO Universität Oldenburg)
Oral presentation I March 18, 2025 I 4.00 p.m. I room 6+7

Evaluating a Binaural Model Using Real-Time Assessment of Listening Effort in Human Listeners
Speaker: Martin Berdau (CvO Universität Oldenburg)
Oral presentation I March 18, 2025 I 4.20 p.m. I room 6+7

Comparison of Noise Detection Methods for Exponential Sine Sweep Measurements
Speaker: Georg Stolz (TU Ilmenau)
Oral presentation I March 19, 2025 I 9.00 a.m. I room 5

Validation of the German Matrix Test in a Remote Testing Application
Speaker: Thomas Schwarz (CvO Universität Oldenburg)
Poster presentation I March 19, 2025 I 3.20 p.m. I room 6+7

Integrating Multiscale Representation And Re-Evaluating Channel Shuffling In Efficient Time-Frequency Separate Networks For Acoustic Scene Classification
Speaker: Yuxuan He (TU Ilmenau)
Poster presentation I March 19, 2025 I 3.20 p.m. I room 20

Challenges of conducting a large-scale online perceptual study in the field of spatial audio
Speaker: Lukas Treybig (TU Ilmenau)
Oral presentation I March 20, 2025 I 2.20 p.m. I room 5

NeuroSensEar: Neuromorphic acoustic sensing for the high-performance hearing aids of tomorrow
Speaker: Claudia Lenk (Universität Ulm)
Oral presentation I March 20, 2025 I 2.40 p.m. I Vesterbro (B3M2)

Comparison of reference-based and single-ended prediction models for perceived listening effort
Speaker: Jan Reimes (HEAD acoustics GmbH)
Poster presentation I March 20, 2025 I 3.00 p.m. I room 19

Insights Into Automated Quality Inspection in Lightweight Additive Manufacturing Using Machine-Learning With Measured and Simulated Acoustic Emissions
Speaker: Sören Keuchel (Novicos GmbH)
Oral presentation I March 20, 2025 I 3.20 p.m. I room 18

Conference

Copenhagen / March 17, 2025 - March 20, 2025

DAS I DAGA 2025 – 51. Annual Meeting on Acoustics

DAGA 2025

Contributions of the Fraunhofer IDMT to DAGA 2025

Real-time assessment of listening effort using non-intrusive binaural prediction models

Analysing Bowel Sound Signals: Insights from SonicGuard Data Collection

Individual Case or a More General Problem? Investigating Altered Localization Cues with Different Level-Dependent Hearing Protection Devices Concerning Worker Safety

Extension of the auditory information in time-frequency representations of audio signals for machine learning applications

Semi-supervised Learning for Acoustic Scene Classification using FixMatch

Bridging The Gap: GANs As A Solution For Data-Scarce Industrial Audio Classification

Investigation of Electroacoustic Properties of Experimental Fibre-Optic Microphone Designs

Variance-maximizing acoustic dimensions for machine learning-based soundscape assessment

Modeling of Microchannel Acoustics: Relevant Phenomena and Acoustic Impedance Models

Multilingual Listening Effort Prediction - LEAP goes international

MPEG Audio Coding for Machines

How does training impact distance perception of warning signals?

Structured Session "Sound Analysis for Music and Audio Signals"

Further contributions to DAGA 2025 in which the Fraunhofer IDMT is involved

Contact Press / Media

Christoph Sladeczek

Contact Press / Media

PD Dr. Jan Rennies-Hochmuth