Dominant speaker detection using discrete Markov chain for multi-user video conferencing

Vishnu Monn Baskaran, Yoong Choon Chang, Jonathan Loo, Koksheik Wong, Ming Tao Gan

Research output: Chapter in Book/Report/Conference proceedingConference PaperOtherpeer-review

1 Citation (Scopus)


This paper puts forward a discrete-time Markov chain algorithm in predicting a pair of active or dominant speakers in an ultra-high definition multi-user video conferencing system. The applied Markov chain minimizes false dominant speaker classification due to transient noise during a video conferencing session. This algorithm also includes a set of linear weights-based assignment for both the initial state vector and transition probability matrix, which improves the response of the algorithm towards changing dominant speakers. Experimental results suggests that this algorithm accurately predicts the most dominant speaker at a rate of 83% for 11 clients in a combined video with 86% reduction in false dominant speaker classification, based on given a set of artificial speaker data.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages2
ISBN (Electronic)9781479987443
Publication statusPublished - 20 Aug 2015
Externally publishedYes
EventIEEE International Conference on Consumer Electronics-Taiwan 2015 - Taipei, Taiwan
Duration: 6 Jun 20158 Jun 2015
Conference number: 2nd (Proceedings)


ConferenceIEEE International Conference on Consumer Electronics-Taiwan 2015
Abbreviated titleICCE-TW 2015
Internet address


  • Bandwidth
  • Classification algorithms
  • Containers
  • Markov processes
  • Noise
  • Prediction algorithms
  • Transient analysis

Cite this