Research on Emergency Parking Instruction Recognition Based on Speech Recognition and Speech Emotion Recognition

In view of the situation that novice drivers are easily out of control in an emergency, this paper proposes an emergency parking instruction recognition system based on speech recognition and speech emotion recognition. The system first extracts the feature vector of the speech signal, and then uses the support vector machine (SVM) to recognize the emotion of the speech. When the emotion is abnormal, the dynamic time warping (DWT) algorithm is used to match the parking instruction template. The test results show that the system can realize the speech recognition of parking instructions very well.