Psychoacoustic Model
Psychoacoustic models aim to mathematically represent how humans perceive sound, focusing on factors beyond simple sound intensity, such as masking, loudness, and spatial perception. Current research emphasizes the development and refinement of these models for applications in diverse fields, including audio watermarking, speech enhancement, and the design of hearing aids and noise-reduction technologies. This involves exploring various algorithms, such as those based on deep learning and filterbank analysis, to improve the accuracy and efficiency of psychoacoustic simulations, ultimately leading to more effective and user-friendly audio technologies.
Papers
Discussion of Features for Acoustic Anomaly Detection under Industrial Disturbing Noise in an End-of-Line Test of Geared Motors
Peter Wissbrock, David Pelkmann, Yvonne Richter
Cutting Through the Noise: An Empirical Comparison of Psychoacoustic and Envelope-based Features for Machinery Fault Detection
Peter Wißbrock, Yvonne Richter, David Pelkmann, Zhao Ren, Gregory Palmer