EUVIMEDEUVIMED entdecken
Crossref

Speech Emotion Recognition via CNN-Transformer and multidimensional attention mechanism

Xiaoyu Tang, Jiazheng Huang, Yixin Lin, Ting Dang, Jintao Cheng

Speech Communication · 2025-06 · 171 · 103242

DOI: 10.1016/j.specom.2025.103242 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Speech Communication, 2025-06. Verfasst von Xiaoyu Tang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Speech Emotion Recognition (SER) is crucial in human-machine interactions. Mainstream approaches utilize Convolutional Neural Networks or Recurrent Neural Networks to learn local energy feature representations of speech segments from speech information, but struggle with capturing global information such as the duration of energy in speech. Some use Transformers to capture global information, but there is room for improvement in terms of parameter count and performance. Furthermore, existing attention mechanisms focus on spatial or channel dimensions, hindering learning of important temporal information in speech. In this paper, to model local and global information at different levels of granularity in speech and capture temporal, spatial and channel dependencies in speech signals, we propose a Speech Emotion Recognition network based on CNN-Transformer and multi-dimensional attention mechanisms. Specifically, a stack of CNN blocks is dedicated to capturing local information in speech from a time-frequency perspective. In addition, a time-channel-space attention mechanism is used to enhance features across three dimensions. Moreover, we model local and global dependencies of feature sequences using large convolutional kernels with depthwise separable convolutions and lightweight Transformer modules. We evaluate the proposed method on IEMOCAP and Emo-DB datasets and show our approach significantly improves the performance over the state-of-the-art methods.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Tang, X., Huang, J., Lin, Y., Dang, T., & Cheng, J. (2025). Speech Emotion Recognition via CNN-Transformer and multidimensional attention mechanism. Speech Communication, 171, 103242. https://doi.org/10.1016/j.specom.2025.103242

Vancouver

Tang X, Huang J, Lin Y, Dang T, Cheng J. Speech Emotion Recognition via CNN-Transformer and multidimensional attention mechanism. Speech Communication. 2025;171:103242. doi:10.1016/j.specom.2025.103242

BibTeX
@article{Tang2025,
  author = {Tang, Xiaoyu and Huang, Jiazheng and Lin, Yixin and Dang, Ting and Cheng, Jintao},
  title = {Speech Emotion Recognition via CNN-Transformer and multidimensional attention mechanism},
  journal = {Speech Communication},
  year = {2025},
  volume = {171},
  pages = {103242},
  doi = {10.1016/j.specom.2025.103242}
}
Kostenlos starten →