Citation

Baskaran, Vishnu Monn and Chang, Yoong Choon and Loo, Jonathan and Wong, Kok Sheik and Gan, Ming Tao (2018) Dominant speaker detection in multipoint video communication using Markov chain with non-linear weights and dynamic transition window. Information Sciences, 463-46. pp. 344-362. ISSN 0020-0255

Text 88.pdf Restricted to Repository staff only Download (2MB)

Abstract

This paper proposes an enhanced discrete-time Markov chain algorithm in predicting dom- inant speaker(s) for multipoint video communication system in the presence of tran- sient speech. The proposed algorithm exploits statistical properties of the past speech patterns to accurately predict the dominant speaker for the next time state. Non-linear weights-based coefficients are employed in the enhanced Markov chain for both the ini- tial state vector and transition probability matrix. These weights significantly improve the time taken to predict a new dominant speaker during a conference session. In addition, a mechanism to dynamically modify the size of the transition probability matrix win- dow/container is introduced to improve the adaptability of the Markov chain towards the variability of speech characteristics. Simulation results indicate that for an 11 con- ference participants test scenario, the enhanced Markov chain prediction algorithm reg- istered an 85% accuracy in predicting a dominant speaker when compared to an ideal case where there is no transient speech. Misclassification of dominant speakers due to transient speech was also reduced by 87%.

Item Type:	Article
Uncontrolled Keywords:	Markov chain, Markov chain, dominant speaker detection, multipoint video communication
Subjects:	Q Science > QA Mathematics > QA273-280 Probabilities. Mathematical statistics
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Nov 2020 10:13
Last Modified:	18 Nov 2020 10:13
URII:	http://shdl.mmu.edu.my/id/eprint/7390

Downloads

Edit (login required)