Emotional recognition from the speech signal for a virtual education agent

7th Sensors & their Applications

Tickle, A.^1 ; Raghu, S.^1 ; Elshaw, M.^2

Department of Aviation, Aerospace Electrical and Electronic Engineering, Faculty of Computing and Engineering, Coventry University, Priory Street, Coventry, United Kingdom^1

Department of Computing, Faculty of Computing and Engineering, Coventry University, Priory Street, Coventry, United Kingdom^2

关键词: Acoustic features;    Emotion recognition;    Emotional recognition;    Emotional speech;    Feature extract;    Recognition of emotion;    Supervised neural networks;    Virtual education;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/450/1/012053/pdf
DOI  :  10.1088/1742-6596/450/1/012053

来源: IOP

【 摘 要 】

This paper explores the extraction of features from the speech wave to perform intelligent emotion recognition. A feature extract tool (openSmile) was used to obtain a baseline set of 998 acoustic features from a set of emotional speech recordings from a microphone. The initial features were reduced to the most important ones so recognition of emotions using a supervised neural network could be performed. Given that the future use of virtual education agents lies with making the agents more interactive, developing agents with the capability to recognise and adapt to the emotional state of humans is an important step.