EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Perception and classification of emotions in nonsense speech: Humans versus machines

Emilia Parada-Cabaleiro iD, Anton Batliner, Maximilian Schmitt iD, Markus Schedl, Giovanni Costantini, Björn Schuller

PLOS ONE · 2023

DOI: 10.1371/journal.pone.0281079 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2023. Verfasst von Emilia Parada-Cabaleiro und 5 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computational Perception, Johannes Kepler University Linz, Linz, Austria. Hauptthemen laut MEDLINE: Speech, Speech Perception. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020 Framework Programme, Austrian Science Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article contributes to a more adequate modelling of emotions encoded in speech, by addressing four fallacies prevalent in traditional affective computing: First, studies concentrate on few emotions and disregard all other ones (‘closed world’). Second, studies use clean (lab) data or real-life ones but do not compare clean and noisy data in a comparable setting (‘clean world’). Third, machine learning approaches need large amounts of data; however, their performance has not yet been assessed by systematically comparing different approaches and different sizes of databases (‘small world’). Fourth, although human annotations of emotion constitute the basis for automatic classification, human perception and machine classification have not yet been compared on a strict basis (‘one world’). Finally, we deal with the intrinsic ambiguities of emotions by interpreting the confusions between categories (‘fuzzy world’). We use acted nonsense speech from the GEMEP corpus, emotional ‘distractors’ as categories not entailed in the test set, real-life noises that mask the clear recordings, and different sizes of the training set for machine learning. We show that machine learning based on state-of-the-art feature representations ( wav2vec2 ) is able to mirror the main emotional categories (‘pillars’) present in perceptual emotional constellations even in degradated acoustic conditions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SpeechSpeech PerceptionHumansEmotionsMachine LearningAcousticsPerception

Autor:innen und Institutionen

  • Institute of Computational Perception, Johannes Kepler University Linz, Linz, Austria.
  • Human-centered AI Group, Linz Institute of Technology (LIT), Linz, Austria.
  • Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany.
  • Department of Electronic Engineering, University of Rome Tor Vergata, Rome, Italy.
  • GLAM-Group on Language, Audio & Music, Imperial College London, London, United Kindom.

ORCID-Profile: Emilia Parada-Cabaleiro, Maximilian Schmitt

Förderung

  • Horizon 2020 Framework Programme
  • Austrian Science Fund

Zitieren

APA

Parada-Cabaleiro, E., Batliner, A., Schmitt, M., Schedl, M., Costantini, G., & Schuller, B. (2023). Perception and classification of emotions in nonsense speech: Humans versus machines. PLOS ONE. https://doi.org/10.1371/journal.pone.0281079

Vancouver

Parada-Cabaleiro E, Batliner A, Schmitt M, Schedl M, Costantini G, Schuller B. Perception and classification of emotions in nonsense speech: Humans versus machines. PLOS ONE. 2023. doi:10.1371/journal.pone.0281079

BibTeX
@article{ParadaCabaleiro2023,
  author = {Parada-Cabaleiro, Emilia and Batliner, Anton and Schmitt, Maximilian and Schedl, Markus and Costantini, Giovanni and Schuller, Björn},
  title = {Perception and classification of emotions in nonsense speech: Humans versus machines},
  journal = {PLOS ONE},
  year = {2023},
  doi = {10.1371/journal.pone.0281079}
}
Kostenlos starten →