Emotion Detection System Based on Speech and Facial Signals
2012
This paper introduces the present status of speech emotion detection. In order to improve the emotion recognition rate of single mode, the bimodal fusion method based on speech and facial expression is proposed. First, we establishes emotional database include speech and facial expression. For different emotions, calm, happy, surprise, anger, sad, we extract ten speech parameters and use the PCA method to detect the speech emotion. Then we analyze the bimodal emotion detection of fusing facial expression information. The experiment results show that the emotion recognition rate with bimodal fusion is about 6 percent points higher than the recognition rate with only speech prosodic features
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
9
References
0
Citations
NaN
KQI