Dynamic Bayesian networks for meeting structuring

Alfred Dielmann, Steve Renals

Research output: Chapter in Book/Report/Conference proceedingConference contribution


The paper is about the automatic structuring of multiparty meetings using audio information. We have used a corpus of 53 meetings, recorded using a microphone array and lapel microphones for each participant. The task was to segment meetings into a sequence of meeting actions, or phases. We have adopted a statistical approach using dynamic Bayesian networks (DBNs). Two DBN architectures were investigated: a two-level hidden Markov model (HMM) in which the acoustic observations were concatenated; and a multistream DBN in which two separate observation sequences were modelled. We have also explored the use of counter variables to constrain the number of action transitions. Experimental results indicate that the DBN architectures are an improvement over a simple baseline HMM, with the multistream DBN with counter constraints producing an action error rate of 6%.
Original languageEnglish
Title of host publicationAcoustics, Speech, and Signal Processing, 2004
Subtitle of host publicationProceedings. (ICASSP '04). IEEE International Conference on (Volume:5 )
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Publication statusPublished - 2004
Event2004 IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP) - Fairmount Queen Elizabeth Hotel, Montreal, Quebec, Canada
Duration: 17 May 200421 May 2004


Conference2004 IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP)
CityMontreal, Quebec


Dive into the research topics of 'Dynamic Bayesian networks for meeting structuring'. Together they form a unique fingerprint.

Cite this