Loading...
Loading...

Go to the content (press return)

Improving detection of acoustic events using audiovisual data and feature level fusion

Author
Butko, T.; Canton, C.; Segura, C.; Giro, X.; Nadeu, C.; Hernando, J.; Casas, J.
Type of activity
Presentation of work at congresses
Name of edition
10th Annual Conference of the International Speech Communication Association
Date of publication
2009
Presentation's date
2009-09
Book of congress proceedings
10th annual conference of the International Speech Communication Association 2009 (INTERSPEECH 2009): Brighton, United Kingdom, 6-10 September 2009
First page
1147
Last page
1150
Repository
http://gps-tsc.upc.es/imatge/_Xgiro/research/publications/2009/interspeech.pdf Open in new window
http://hdl.handle.net/2117/85340 Open in new window
URL
http://www.isca-speech.org/archive/interspeech_2009/i09_1147.html Open in new window
Abstract
The detection of the acoustic events (AEs) that are naturally produced in a meeting room may help to describe the human and social activity that takes place in it. When applied to spontaneous recordings, the detection of AEs from only audio information shows a large amount of errors, which are mostly due to temporal overlapping of sounds. In this paper, a system to detect and recognize AEs using both audio and video information is presented. A feature-level fusion strategy is used, and the ...
Citation
Butko, T., Canton, C., Segura, C., Giro, X., Nadeu, C., Hernando, J., Casas, J. Improving detection of acoustic events using audiovisual data and feature level fusion. A: Annual Conference of the International Speech Communication Association. "ISCA-INST Speech Communication Association". 2009, p. 1147-1150.
Keywords
acoustic event detection, acoustic localization, hidden Markov models, multimodal fusion, multimodality
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications
VEU - Speech Processing Group

Participants

Attachments