English

Speech Emotion Recognition Using Quaternion Convolutional Neural Networks

Sound 2021-11-02 v1 Computation and Language Audio and Speech Processing

Abstract

Although speech recognition has become a widespread technology, inferring emotion from speech signals still remains a challenge. To address this problem, this paper proposes a quaternion convolutional neural network (QCNN) based speech emotion recognition (SER) model in which Mel-spectrogram features of speech signals are encoded in an RGB quaternion domain. We show that our QCNN based SER model outperforms other real-valued methods in the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS, 8-classes) dataset, achieving, to the best of our knowledge, state-of-the-art results. The QCNN also achieves comparable results with the state-of-the-art methods in the Interactive Emotional Dyadic Motion Capture (IEMOCAP 4-classes) and Berlin EMO-DB (7-classes) datasets. Specifically, the model achieves an accuracy of 77.87\%, 70.46\%, and 88.78\% for the RAVDESS, IEMOCAP, and EMO-DB datasets, respectively. In addition, our results show that the quaternion unit structure is better able to encode internal dependencies to reduce its model size significantly compared to other methods.

Keywords

Cite

@article{arxiv.2111.00404,
  title  = {Speech Emotion Recognition Using Quaternion Convolutional Neural Networks},
  author = {Aneesh Muppidi and Martin Radfar},
  journal= {arXiv preprint arXiv:2111.00404},
  year   = {2021}
}

Comments

Published in ICASSP 2021

R2 v1 2026-06-24T07:19:31.457Z