logo Idiap Research Institute        
 [BibTeX] [Marc21]
Unsupervised Location-Based Segmentation of Multi-Party Speech
Type of publication: Conference paper
Citation: lathoud04a
Booktitle: Proceedings of the 2004 ICASSP-NIST Meeting Recognition Workshop
Year: 2004
Month: 5
Address: Montreal, Canada
Note: IDIAP-RR 04-14
Crossref: lathoud-rr-04-14:
Abstract: Accurate detection and segmentation of spontaneous multi-party speech is crucial for a variety of applications, including speech acquisition and recognition, as well as higher-level event recognition. However, the highly sporadic nature of spontaneous speech makes this task difficult. Moreover, multi-party speech contains many overlaps. We propose to attack this problem as a tracking task, using location cues only. In order to best deal with high sporadicity, we propose a novel, generic, short-term clustering algorithm that can track multiple objects for a low computational cost. The proposed approach is online, fully deterministic and can run in real-time. In an application to real meeting data, the algorithm produces high precision speech segmentation.
Userfields: ipdinar={2004}, ipdmembership={speech, vision},
Projects Idiap
Authors Lathoud, Guillaume
McCowan, Iain A.
Odobez, Jean-Marc
Added by: [UNK]
Total mark: 0
  • lathoud04a.pdf
  • lathoud04a.ps.gz