Abstract
Accurate emotion recognition from speech is important for applications like smart health care, smart entertainment, and other smart services. High accuracy emotion recognition from Chinese speech is challenging due to the complexities of the Chinese language. In this paper, we explore how to improve the accuracy of speech emotion recognition, including speech signal feature extraction and emotion classification methods. Five types of features are extracted from a speech sample: mel frequency cepstrum coefficient (MFCC), pitch, formant, short-term zero-crossing rate and short-term energy. By comparing statistical features with deep features extracted by a Deep Belief Network (DBN), we attempt to find the best features to identify the emotion status for speech. We propose a novel classification method that combines DBN and SVM (support vector machine) instead of using only one of them. In addition, a conjugate gradient method is applied to train DBN in order to speed up the training process. Gender-dependent experiments are conducted using an emotional speech database created by the Chinese Academy of Sciences. The results show that DBN features can reflect emotion status better than artificial features, and our new classification approach achieves an accuracy of 95.8%, which is higher than using either DBN or SVM separately. Results also show that DBN can work very well for small training databases if it is properly designed.
Highlights
Emotion is a mixture of people’s physiological response and inner thoughts and plays an important role in rational actions and decision making for human beings
In the pre-emphasis step, a Finite Impulse Response (FIR) filter which is called pre-emphasis filter is used on the speech signal
The speech data was recorded in a pure acoustic environment with 35 db signal-to-noise ratio (SNR), 16000 HZ sampling rate, 16 bit rate, and stored as PCM format
Summary
Emotion is a mixture of people’s physiological response and inner thoughts and plays an important role in rational actions and decision making for human beings. Automatic emotion recognition from speech has been an active research topic for applications such as smart health care, smart home, smart entertainment, and many other smart services. Much research has been done towards recognizing human emotions using speech information [1,2,3]. There is little research on emotion recognition in Chinese speech, which is more challenging because of complexities arising from Chinese language’s prosodic characteristics. Two of the most important types of information are verbal content and emotion status, both of which can be distinguished relatively more by humans than by computers. Emotional status are represented by many features, so extracting suitable features from speech signals that can effectively characterize different emotions is crucial. In the pre-emphasis step, a Finite Impulse Response (FIR) filter which is called pre-emphasis filter is used on the speech signal.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
