@article{VersuemerBlaettermannRosenthaletal.2025, author = {Vers{\"u}mer, Siegbert and Bl{\"a}ttermann, Patrick and Rosenthal, Fabian and Weinzierl, Stefan}, title = {A comparison of methods for modeling soundscape dimensions based on different datasets}, series = {The Journal of the Acoustical Society of America}, volume = {157}, journal = {The Journal of the Acoustical Society of America}, number = {1}, publisher = {AIP Publishing}, issn = {1520-8524}, doi = {10.1121/10.0034849}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-48849}, pages = {234 -- 255}, year = {2025}, abstract = {Soundscape studies vary considerably in study design, statistical methods, and model fit metrics used. Due to this confounding of data and methods, it is difficult to assess the suitability of statistical modelling techniques used in the literature. Therefore, five different methods and two performance metrics were applied to three existing soundscape datasets to model soundscape Pleasantness and Eventfulness based on seven acoustic and three sociodemographic predictors. Datasets differed in soundscape type (urban outdoor vs indoor), experimental setting (field- vs lab-based), size, and study design (site- vs person-centered). The fixed-effects and mixed-effects methods ranged from linear to nonlinear regression based on advanced machine learning approaches. Results showed that models performed better for Eventfulness than for Pleasantness in most cases, while performance as measured by the out-of-sample R2 was dependent on the total variance of the target, especially in both field studies with imbalanced targets and groups. Nonlinear methods consistently outperformed linear regression, with random forest and extreme gradient boosting performing particularly well, while the performance levels of all nonlinear methods remained comparable. Mixed-effects models provided a more generalized, albeit slightly smaller prediction performance when tested on unknown groups. Finally, this study motivates the use of cross-validation with special splitting for analyzing small imbalanced datasets.}, subject = {Akustische Eigenschaft}, language = {en} } @article{VersuemerSteffensWeinzierl2023, author = {Vers{\"u}mer, Siegbert and Steffens, Jochen and Weinzierl, Stefan}, title = {Day-to-day loudness assessments of indoor soundscapes: Exploring the impact of loudness indicators, person, and situation}, series = {The Journal of the Acoustical Society of America}, volume = {153}, journal = {The Journal of the Acoustical Society of America}, number = {5}, publisher = {Acoustical Society of America (ASA)}, issn = {0001-4966}, doi = {10.1121/10.0019413}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-46127}, pages = {2956 -- 2972}, year = {2023}, abstract = {This study investigates loudness perception in real-world contexts using predictors related to the sound, situation, or person. In the study, 105 participants recorded 6594 sound environments in their homes, which were then evaluated based on the Experience Sampling Method. Hierarchical linear regressions using a loudness level based on ISO 532-1 allowed for obtaining the best model fits for predicting perceived loudness and explaining the highest variance. LAeq and LAF5 provided comparable results and may require less computational effort. However, the analysis shows that only one-third of the variance explained by fixed effects was attributable to the loudness level. Sixteen percent stemmed from perceived properties of the soundscape; 1\% were attributable to relatively temporally stable, person-related predictors like participants' age; non-auditory situational predictors made no additional contribution. The results thus did not confirm previous findings on loudness perception under laboratory conditions, emphasizing the importance of the situational context. Along with the current paper, a comprehensive dataset, including the assessed person-related, situational, and sound-related measures as well as LAeq time-series and third-octave spectrograms, is provided to enable further research on sound perception, indoor soundscapes, and emotion.}, subject = {Lautwahrnehmung}, language = {en} }