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}, |
| Keywords: | |
| Projects: |
Idiap |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
