A5000696935- Deception detection and forensic psychology
- Speech and Audio Processing
- Wireless Signal Modulation Classification
- Misinformation and Its Impacts
- Anomaly Detection Techniques and Applications
- Traffic and Road Safety
- Speech Recognition and Synthesis
- Power Systems and Renewable Energy
- Advanced Battery Technologies Research
- Interconnection Networks and Systems
- Video Surveillance and Tracking Methods
- Embedded Systems Design Techniques
- Autonomous Vehicle Technology and Safety
- Parallel Computing and Optimization Techniques
- Advanced Malware Detection Techniques
- Emotion and Mood Recognition
University of Electronic Science and Technology of China
2022-2024
Henan University of Technology
2019
Speech is the most effective way for people to exchange complex information. Recognition of emotional information contained in speech one important challenges field artificial intelligence. To better acquire features signals, a parallelized convolutional recurrent neural network (PCRN) with spectral proposed emotion recognition. First, frame-level are extracted from each utterance and, long short-term memory employed learn these frame by frame. At same time, deltas and delta-deltas log...
Existing algorithms of speech-based deception detection are severely restricted by the lack sufficient number labelled data. However, a large amount easily available unlabelled data has not been utilized in reality. To solve this problem, paper proposes semi-supervised additive noise autoencoder model for detection. This updates and optimizes it consists two layers encoder decoder, classifier. Firstly, changes activation function hidden layer network according to characteristics speech....
In order to make full use of the advantages speech-based deception detection, such as high concealment, low cost and easy operation, a detection algorithm based on Support Vector Machine (SVM) acoustic features (AF-SVM) is proposed. Firstly, corpus containing 388 speech data constructed. Then, zero-crossing rate, pitch short-term energy and, Mel frequency cepstral coefficients other are extracted normalized. Finally, SVM classifier used train classify acquired feature data. The experimental...
The pedestrian trajectory prediction is critical for autonomous driving, intelligent navigation, and abnormal behavior detection. With the booming of artificial intelligence (AI), many researchers have employed deep learning technologies to solve problem obtained relatively better performance in short-term prediction. However, long-term still challenging achieve high accuracy. In this work, we propose a space-time tree search (STTS) method Compared with existing methods only considering from...