EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Small Language Models for Speech Emotion Recognition in Text and Audio Modalities

José L. Gómez-Sirvent, Francisco López de la Rosa, Daniel Sánchez-Reolid, Roberto Sánchez-Reolid, Antonio Fernández-Caballero

Applied Sciences · 10.07.2025 · 15 (14) · 7730

DOI: 10.3390/app15147730 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 10.07.2025. Verfasst von José L. Gómez-Sirvent und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 99 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Spanish MCIU/AEI/10.13039/501100011033/ ERDF, EU, Universidad de Castilla-La Mancha, MICIU/AEI/10.13039/501100011033.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speech emotion recognition has become increasingly important in a wide range of applications, driven by the development of large transformer-based natural language processing models. However, the large size of these architectures limits their usability, which has led to a growing interest in smaller models. In this paper, we evaluate nineteen of the most popular small language models for the text and audio modalities for speech emotion recognition on the IEMOCAP dataset. Based on their cross-validation accuracy, the best architectures were selected to create ensemble models to evaluate the effect of combining audio and text, as well as the effect of incorporating contextual information on model performance. The experiments conducted showed a significant increase in accuracy with the inclusion of contextual information and the combination of modalities. The results obtained were highly competitive, outperforming numerous recent approaches. The proposed ensemble model achieved an accuracy of 82.12% on the IEMOCAP dataset, outperforming several recent approaches. These results demonstrate the effectiveness of ensemble methods for improving speech emotion recognition performance, and highlight the feasibility of training multiple small language models on consumer-grade computers.

Förderung

  • Spanish MCIU/AEI/10.13039/501100011033/ ERDF, EU
  • Universidad de Castilla-La Mancha
  • MICIU/AEI/10.13039/501100011033
  • Programa Iberoamericano de Ciencia y Tecnología para el Desarrollo (CYTED)

Zitieren

APA

Gómez-Sirvent, J. L., Rosa, F. L. D. L., Sánchez-Reolid, D., Sánchez-Reolid, R., & Fernández-Caballero, A. (2025). Small Language Models for Speech Emotion Recognition in Text and Audio Modalities. Applied Sciences, 15(14), 7730. https://doi.org/10.3390/app15147730

Vancouver

Gómez-Sirvent JL, Rosa FLDL, Sánchez-Reolid D, Sánchez-Reolid R, Fernández-Caballero A. Small Language Models for Speech Emotion Recognition in Text and Audio Modalities. Applied Sciences. 2025;15(14):7730. doi:10.3390/app15147730

BibTeX
@article{GmezSirvent2025,
  author = {Gómez-Sirvent, José L. and Rosa, Francisco López de la and Sánchez-Reolid, Daniel and Sánchez-Reolid, Roberto and Fernández-Caballero, Antonio},
  title = {Small Language Models for Speech Emotion Recognition in Text and Audio Modalities},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {14},
  pages = {7730},
  doi = {10.3390/app15147730}
}
Kostenlos starten →