EUVIMEDEUVIMED entdecken
Crossref

Testing Correctness, Fairness, and Robustness of Speech Emotion Recognition Models

Anna Derington, Hagen Wierstorf, Ali Özkil, Florian Eyben, Felix Burkhardt, Björn W. Schuller

IEEE Transactions on Affective Computing · 2025-07 · 16 (3) · 1929-1941

DOI: 10.1109/taffc.2025.3547218 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Affective Computing, 2025-07. Verfasst von Anna Derington und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 73 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning models for speech emotion recognition (SER) can be trained for different tasks and are usually evaluated based on a few available datasets per task. Tasks could include arousal, valence, dominance, emotional categories, or tone of voice. Those models are mainly evaluated in terms of correlation or recall, and always show some errors in their predictions. The errors manifest themselves in model behaviour, which can be very different along different dimensions even if the same recall or correlation is achieved by the model. This paper introduces a testing framework to investigate behaviour of speech emotion recognition models, by requiring different metrics to reach a certain threshold in order to pass a test. The test metrics can be grouped in terms of correctness, fairness, and robustness. It also provides a method for automatically specifying test thresholds for fairness tests, based on the datasets used, and recommendations on how to select the remaining test thresholds. We evaluated a xLSTM-based and nine transformer-based acoustic foundation models against a convolutional baseline model, testing their performance on arousal, valence, dominance, and emotional category classification. The test results highlight, that models with high correlation or recall might rely on shortcuts – such as text sentiment –, and differ in terms of fairness.

Zitieren

APA

Derington, A., Wierstorf, H., Özkil, A., Eyben, F., Burkhardt, F., & Schuller, B. W. (2025). Testing Correctness, Fairness, and Robustness of Speech Emotion Recognition Models. IEEE Transactions on Affective Computing, 16(3), 1929-1941. https://doi.org/10.1109/taffc.2025.3547218

Vancouver

Derington A, Wierstorf H, Özkil A, Eyben F, Burkhardt F, Schuller BW. Testing Correctness, Fairness, and Robustness of Speech Emotion Recognition Models. IEEE Transactions on Affective Computing. 2025;16(3):1929-1941. doi:10.1109/taffc.2025.3547218

BibTeX
@article{Derington2025,
  author = {Derington, Anna and Wierstorf, Hagen and Özkil, Ali and Eyben, Florian and Burkhardt, Felix and Schuller, Björn W.},
  title = {Testing Correctness, Fairness, and Robustness of Speech Emotion Recognition Models},
  journal = {IEEE Transactions on Affective Computing},
  year = {2025},
  volume = {16},
  number = {3},
  pages = {1929--1941},
  doi = {10.1109/taffc.2025.3547218}
}
Kostenlos starten →