Predicting human response to complex sound is a nontrivial task. Besides large differences among subjects and practically infinite types of stimuli, human response to sound is typically quantified by a few parameters having nonlinear behavior. Still, such predictions are valuable for the assessment of sound quality, which is a critical step toward the development of systems that offer improved human comfort, productivity and wellness. The overall objective of this work is to learn about human perception of sound through the use of machine learning algorithms. Learning algorithms are ideal for modeling the complex behavior of subjective parameters and identifying new trends with the potential to accumulate knowledge from different experiments. This work compares the performance of four learning algorithms (linear regression, support vector machines, decision trees, and random forests) to predict annoyance due to complex sound. Construction of these models relies on the annoyance response of 38 subjects to 103 sounds described by five known predictors (loudness, roughness, sharpness, tonality, and fluctuation strength). Comparison of these algorithms in terms of prediction accuracy, model interpretability, versatility, and computation time indicates that decision trees and random forests are the best algorithms for this task.
Skip Nav Destination
Article navigation
March 2018
Meeting abstract. No PDF available.
March 01 2018
Assessment of learning algorithms to model perception of sound
Menachem Rafaelof;
Menachem Rafaelof
NIA-NASA Langley Res. Ctr., M.S. 463, 100 Exploration Way, Hampton, VA 23681-2199, [email protected]
Search for other works by this author on:
Andrew Schroeder
Andrew Schroeder
Acoust. Branch, NASA Langley Res. Ctr., Lancaster, OH
Search for other works by this author on:
J. Acoust. Soc. Am. 143, 1741 (2018)
Connected Content
A companion article has been published:
Investigation of machine learning algorithms to model perception of sound
Citation
Menachem Rafaelof, Andrew Schroeder; Assessment of learning algorithms to model perception of sound. J. Acoust. Soc. Am. 1 March 2018; 143 (3_Supplement): 1741. https://doi.org/10.1121/1.5035683
Download citation file:
327
Views
Citing articles via
All we know about anechoic chambers
Michael Vorländer
A survey of sound source localization with deep learning methods
Pierre-Amaury Grumiaux, Srđan Kitić, et al.
Does sound symbolism need sound?: The role of articulatory movement in detecting iconicity between sound and meaning
Mutsumi Imai, Sotaro Kita, et al.
Related Content
Analyzing technical, sentimental, and machine learning algorithms for stock market prediction
AIP Conf. Proc. (July 2024)
Student perceptions and achievements of online learning: Machine learning approaches
AIP Conference Proceedings (November 2022)
Using machine learning to evaluate the fidelity of acoustic simulations
J. Acoust. Soc. Am. (October 2020)
Establishing an audibility sensitivity rule for low-frequency tone complexes in noise
J. Acoust. Soc. Am. (October 2019)
Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty
Physics of Fluids (August 2015)