Automatic Analysis of Multimodal Group Actions in Meetings
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-stage Speaker Diarization for Conference and Lecture Meetings
Multimodal Technologies for Perception of Humans
Body posture identification using hidden Markov model with a wearable sensor network
BodyNets '08 Proceedings of the ICST 3rd international conference on Body area networks
Speaker diarization using autoassociative neural networks
Engineering Applications of Artificial Intelligence
Wireless sensor networks for personal health monitoring: Issues and an implementation
Computer Communications
Variational bayesian methods for audio indexing
MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
Computationally Efficient and Robust BIC-Based Speaker Segmentation
IEEE Transactions on Audio, Speech, and Language Processing
Speaker Diarization: A Review of Recent Research
IEEE Transactions on Audio, Speech, and Language Processing
Hi-index | 0.00 |
This paper presents speaker diarization using low cost wearable wireless sensors. A prototype Wireless Body Area Network (WBAN) has been constructed for experimentally acoustic diarization for human interaction monitoring in the presence of low acoustic data sampling frequency, noise and altered distance. The key idea is to collect the acoustic-modal sensor data from strategically placed wireless sensors over a human subject's body, and to process that using ACD in order to identify the instantaneous speaker. Through experiments, with body mounted sensors, it is demonstrated that the proposed system, Acoustic Comparator based Diarization (ACD), can be used for effective acoustic diarization with high precision. Controlled experiments using human subjects were carried out for evaluating the performance of ACD acoustic diarization.