Refine
Document Type
- Conference Proceeding (8)
- Article (4)
- Researchdata (3)
- Part of a Book (1)
- Doctoral Thesis (1)
Is part of the Bibliography
- yes (17)
Keywords
- Lautstärke (6)
- Psychoakustik (6)
- Lautwahrnehmung (5)
- Regressionsanalyse (3)
- Soundscape (3)
- Acoustic ecology (2)
- Acoustical properties (2)
- Akustische Eigenschaft (2)
- Audiometrie (2)
- Audiometry (2)
Department/institution
Audioinhaltsanalyse und Multilevelmodellierung zur Vorhersage der Bewertung von Indoor Soundscapes
(2022)
The soundscape approach highlights the role of situational factors in sound evaluations; however, only a few studies have applied a multi‐domain approach including sound‐related, person‐related, and time‐varying situational variables. Therefore, we conducted a study based on the Experience Sampling Method to measure the relative contribution of a broad range of potentially relevant acoustic and non‐auditory variables in predicting indoor soundscape evaluations. Here we present the comprehensive dataset for which 105 participants reported temporally (rather) stable trait variables such as noise sensitivity, trait affect, and quality of life. They rated 6.594 situations regarding the soundscape standard dimensions, perceived loudness, and the saliency of its sound components and evaluated situational variables such as state affect, perceived control, activity, and location. To complement these subject‐centered data, we additionally crowdsourced object‐centered data by having participants make binaural measurements of each indoor soundscape at their homes using a low‐(self‐)noise recorder. These recordings were used to compute (psycho‐)acoustical indices such as the energetically averaged loudness level, the A‐weighted energetically averaged equivalent continuous sound pressure level, and the A‐weighted five‐percent exceedance level. This complex hierarchical data can be used to investigate time‐varying non‐auditory influences on sound perception and to develop soundscape indicators based on the binaural recordings to predict soundscape evaluations.
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.
The evaluation of listening experiments and studies on acoustics not only requires basic knowledge of statistics, but also poses challenges in the implementation of different methodologies. Especially for small sample sizes and peculiarities regarding hierarchical data structures, the need to individualize evaluation scripts arises. Therefore, we introduce flexcv, a powerful machine learning package for Python for evaluating various models on experimental tabular data, especially with small sample sizes. It supports random effects evaluation (including random slopes) for both linear and non-linear regressors, providing broad applicability to different experiments and research questions.flexcv quickly allows to perform nested cross-validation on a variety of models for comparison with each other. On the one hand, the implementation of a flexible interface simplifies the exchange of methods in the script, allowing researchers to change cross-validation methods without having to touch the actual cross-validation code. On the other hand, extensive online logging allows and simplifies the evaluation and experiment tracking along the process and different machines.
The development of the ISO 12913 has led to the creation of standardized methodologies for collecting and analyzing individual responses regarding acoustic environments in context, with the aim of enabling comparability, replicability, and the development of modelling algorithms in soundscape prediction and design tasks. The development of methods to represent and explore soundscape data has the potential to facilitate deeper insights into different datasets. Although it is unlikely that any single method will sufficiently capture all information in empirical studies, attempts are worthwhile to facilitate advancements in this realm. Therefore, we propose a web application that fosters an interactive exploration of datasets based on the ISO 12913. The application facilitates a comprehensive soundscape search using the 8 items of the standard, 8 features characterizing the soundscape (e.g., intensities of natural, human, and technical sound sources heard), and 10 distinct acoustic features. The search encompasses all possible combinations of these components, thus facilitating detailed exploration, offering an in-depth dataset overview, and enabling the comparison of different datasets. Further functionalities include text searching and the option to download, save, and load selected soundscapes, enhancing control and flexibility in the design of empirical studies and supporting urban planners in understanding various soundscape items.
Understanding people's perception of everyday sound involves a complex interplay of various acoustic and non-acoustic factors. Our objective is to uncover important predictors for predicting real indoor soundscapes. To this end, we re-analyzed soundscape data recorded and evaluated by individuals in their homes, aiming for the utmost ecological validity. Given the intricate nature of sound perception and potential non-linear effects of acoustic and psychoacoustic predictors, we utilized machine-learning methods combined with hierarchical linear modeling to analyze 6375 soundscapes from 96 participants including acoustical, psychoacoustical, as well as situational und person-related predictors. Based on this analysis, we measured both the variability within and between subjects and obtained model fits for the prediction of both soundscape pleasantness and eventfulness. In order to discuss cases where predictions for known individuals or places are of interest, we employed (nested) cross-validation using different data-splitting methods. By doing so, our study sheds light on the generalizability of empirical findings when predicting soundscape evaluations for unknown or known subjects and thus supports a deeper understanding of everyday sound perception.