Edinburgh Research Explorer

DBN Based Joint Dialogue Act Recognition of Multiparty Meetings

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

Related Edinburgh Organisations

Documents

Original languageEnglish
Title of host publication2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages133-136
Number of pages4
Volume4
ISBN (Electronic)1-4244-0728-1
ISBN (Print)1-4244-0727-3
DOIs
Publication statusPublished - 2007
Event2007 IEEE International Conference on Acoustics, Speech and Signal Processing - Hawaii Convention Center, Honolulu, Hawaii, United States
Duration: 15 Apr 200720 Apr 2007

Conference

Conference2007 IEEE International Conference on Acoustics, Speech and Signal Processing
CountryUnited States
CityHonolulu, Hawaii
Period15/04/0720/04/07

Abstract

Joint dialogue act segmentation and classification of the new AMI meeting corpus has been performed through an integrated framework based on a switching dynamic Bayesian network and a set of continuous features and language models. The recognition process is based on a dictionary of 15 DA classes tailored for group decision-making. Experimental results show that a novel interpolated factored language model results in a low error rate on the automatic segmentation task, and thus good recognition results can be achieved on AMI multiparty conversational speech

    Research areas

  • DA, DBN, Interpolated FLM, AMI

Event

2007 IEEE International Conference on Acoustics, Speech and Signal Processing

15/04/0720/04/07

Honolulu, Hawaii, United States

Event: Conference

Download statistics

No data available

ID: 27373778