EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Corpus Speech Emotion Recognition Based on Multi-Task Learning and Subdomain Adaptation

Hongliang Fu, Zhihao Zhuang, Yang Wang, Chen Huang, Wenzhuo Duan

Entropy · 07.01.2023 · 25 (1) · 124

DOI: 10.3390/e25010124 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 07.01.2023. Verfasst von Hongliang Fu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Project of Henan Education Department, Start-up Fund for High-level Talents of Henan University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To solve the problem of feature distribution discrepancy in cross-corpus speech emotion recognition tasks, this paper proposed an emotion recognition model based on multi-task learning and subdomain adaptation, which alleviates the impact on emotion recognition. Existing methods have shortcomings in speech feature representation and cross-corpus feature distribution alignment. The proposed model uses a deep denoising auto-encoder as a shared feature extraction network for multi-task learning, and the fully connected layer and softmax layer are added before each recognition task as task-specific layers. Subsequently, the subdomain adaptation algorithm of emotion and gender features is added to the shared network to obtain the shared emotion features and gender features of the source domain and target domain, respectively. Multi-task learning effectively enhances the representation ability of features, a subdomain adaptive algorithm promotes the migrating ability of features and effectively alleviates the impact of feature distribution differences in emotional features. The average results of six cross-corpus speech emotion recognition experiments show that, compared with other models, the weighted average recall rate is increased by 1.89~10.07%, the experimental results verify the validity of the proposed model.

Schlagwörter

Stichwörter der Autor:innen

feature distributionmulti-task learningspeech emotion recognitionsubdomain adaptation

Autor:innen und Institutionen

  • College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China.
  • Henan Engineering Laboratory of Grain IOT Technology, Henan University of Technology, Zhengzhou 450001, China.
  • Key Laboratory of Food Information Processing and Control, Ministry of Education, Henan University of Technology, Zhengzhou 450001, China.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Project of Henan Education Department
  • Start-up Fund for High-level Talents of Henan University of Technology

Zitieren

APA

Fu, H., Zhuang, Z., Wang, Y., Huang, C., & Duan, W. (2023). Cross-Corpus Speech Emotion Recognition Based on Multi-Task Learning and Subdomain Adaptation. Entropy, 25(1), 124. https://doi.org/10.3390/e25010124

Vancouver

Fu H, Zhuang Z, Wang Y, Huang C, Duan W. Cross-Corpus Speech Emotion Recognition Based on Multi-Task Learning and Subdomain Adaptation. Entropy. 2023;25(1):124. doi:10.3390/e25010124

BibTeX
@article{Fu2023,
  author = {Fu, Hongliang and Zhuang, Zhihao and Wang, Yang and Huang, Chen and Duan, Wenzhuo},
  title = {Cross-Corpus Speech Emotion Recognition Based on Multi-Task Learning and Subdomain Adaptation},
  journal = {Entropy},
  year = {2023},
  volume = {25},
  number = {1},
  pages = {124},
  doi = {10.3390/e25010124}
}
Kostenlos starten →