Emotion recognition using IG-based feature compensation and continuous support vector machines

Chung Hsien Wu, Ze Jing Chuang

研究成果: Conference contribution

摘要

This paper presents an approach to feature compensation for emotion recognition from speech signals. In this approach, the intonation groups (IGs) of the input speech signals are firstly extracted. The speech features in each selected intonation group are then extracted. With the assumption of linear mapping between feature spaces in different emotional states, a feature compensation approach is proposed to characterize the feature space with better discriminability among emotional states. The compensation vector with respect to each emotional state is estimated using the Minimum Classification Error (MCE) algorithm. For the final emotional state decision, the IG-based feature vectors compensated by the compensation vectors are used to train the Continuous Support Vector Machine (CSVMs) for each emotional state. The emotional state with the maximal output probability is determined as the final output. The kernel function of CSVM model is experimentally decided as Radial basis function and the experimental result shows that IG-based feature extraction and compensation can obtain encouraging performance for emotion recognition.

原文English
主出版物標題3rd International Conference on Speech Prosody 2006
編輯R. Hoffmann, H. Mixdorff
發行者International Speech Communications Association
ISBN(電子)9780000000002
出版狀態Published - 2006
事件3rd International Conference on Speech Prosody, SP 2006 - Dresden, Germany
持續時間: 2006 五月 22006 五月 5

出版系列

名字Proceedings of the International Conference on Speech Prosody
ISSN(列印)2333-2042

Conference

Conference3rd International Conference on Speech Prosody, SP 2006
國家Germany
城市Dresden
期間06-05-0206-05-05

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Linguistics and Language

指紋 深入研究「Emotion recognition using IG-based feature compensation and continuous support vector machines」主題。共同形成了獨特的指紋。

引用此