EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MelTrans: Mel-Spectrogram Relationship-Learning for Speech Emotion Recognition via Transformers

Hui Li, Jiawen Li, Hai Liu, Tingting Liu iD, Qiang Chen, Xinge You

Sensors · 25.08.2024 · 24 (17) · 5506

DOI: 10.3390/s24175506 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.08.2024. Verfasst von Hui Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China. Hauptthemen laut MEDLINE: Emotions, Speech. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of Hubei Province project, Jiangxi Provincial Natural Science Foundation, university teaching reform research project of Jiangxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speech emotion recognition (SER) is not only a ubiquitous aspect of everyday communication, but also a central focus in the field of human–computer interaction. However, SER faces several challenges, including difficulties in detecting subtle emotional nuances and the complicated task of recognizing speech emotions in noisy environments. To effectively address these challenges, we introduce a Transformer-based model called MelTrans, which is designed to distill critical clues from speech data by learning core features and long-range dependencies. At the heart of our approach is a dual-stream framework. Using the Transformer architecture as its foundation, MelTrans deciphers broad dependencies within speech mel-spectrograms, facilitating a nuanced understanding of emotional cues embedded in speech signals. Comprehensive experimental evaluations on the EmoDB (92.52%) and IEMOCAP (76.54%) datasets demonstrate the effectiveness of MelTrans. These results highlight MelTrans’s ability to capture critical cues and long-range dependencies in speech data, setting a new benchmark within the context of these specific datasets. These results highlight the effectiveness of the proposed model in addressing the complex challenges posed by SER tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmotionsSpeechHumansAlgorithmsSpeech Recognition Software

Stichwörter der Autor:innen

Transformerdeep learningfeature extractionspeech emotion recognition

Autor:innen und Institutionen

  • School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China.
  • National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China.

ORCID-Profile: Tingting Liu

Förderung

  • National Natural Science Foundation of Hubei Province project
  • Jiangxi Provincial Natural Science Foundation
  • university teaching reform research project of Jiangxi Province
  • Shenzhen Science and Technology Program

Zitieren

APA

Li, H., Li, J., Liu, H., Liu, T., Chen, Q., & You, X. (2024). MelTrans: Mel-Spectrogram Relationship-Learning for Speech Emotion Recognition via Transformers. Sensors, 24(17), 5506. https://doi.org/10.3390/s24175506

Vancouver

Li H, Li J, Liu H, Liu T, Chen Q, You X. MelTrans: Mel-Spectrogram Relationship-Learning for Speech Emotion Recognition via Transformers. Sensors. 2024;24(17):5506. doi:10.3390/s24175506

BibTeX
@article{Li2024,
  author = {Li, Hui and Li, Jiawen and Liu, Hai and Liu, Tingting and Chen, Qiang and You, Xinge},
  title = {MelTrans: Mel-Spectrogram Relationship-Learning for Speech Emotion Recognition via Transformers},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {17},
  pages = {5506},
  doi = {10.3390/s24175506}
}
Kostenlos starten →