Vision and RFID data fusion for tracking people in crowds by a mobile robot
Computer Vision and Image Understanding
Combining dynamic texture and structural features for speaker identification
Proceedings of the 2nd ACM workshop on Multimedia in forensics, security and intelligence
| Hi-index | 0.01 |
In this paper, we present a multimodal audio-visual speaker identification system. The proposed system decomposes the information existing in a video stream into two components: speech and lip motion. It has been studied that lip information not only presents speech information but also characteristic information about a person's identity. Fusing this information with speech information will produce robust person identification under adverse condition. Gaussian mixture models (GMMs) and Hidden markov models (HMMs) are used throughout this work for the tasks of text dependent speaker recognition and mouth tracking. The performance is evaluated for dataset of 22 Indian of different ethnicity speakers each uttering a sentence. The results show that the performance of the biometric system is significantly better when both audio and video features are used Keywords: Biometrics, Speaker recognition, Speaker model, Audio visual speech recognition