How to Put It Into Words - Using Random Forests to Extract Symbol Level Descriptions from Audio Content for Concept Detection

TitleHow to Put It Into Words - Using Random Forests to Extract Symbol Level Descriptions from Audio Content for Concept Detection
Publication TypeConference Paper
Year of Publication2012
AuthorsHuang, P-S., Mertens R., Divakaran A., Friedland G., & Hasegawa-Johnson M.
Page(s)505-508
Other Numbers3241
Abstract

This paper presents a system that uses symbolic representations of audio concepts as words for the descriptions of audio tracks, that enable it to go beyond the state of the art, which is audio event classification of a small number of audio classes in constrained settings, to large-scale classification in the wild. These audio words might be less meaningful for an annotator but they are descriptive for computer algorithms. We devise a random-forest vocabulary learning method with an audio word weighting scheme based on TF-IDF and TD-IDD, so as to combine the computational simplicity and accurate multi-class classification of the random forest with the data-driven discriminative power of the TF-IDF/TD-IDD methods. The proposed random forest clustering with text-retrieval methods significantly outperforms two state-of-the-art methods on the dry-run set and the full set of the TRECVID MED 2010 dataset.

URLhttp://www.icsi.berkeley.edu/pubs/speech/ICSI_howtoputitintowords12.pdf
Bibliographic Notes

Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp. 505-508, Kyoto, Japan

Abbreviated Authors

P.-S. Huang, R. Mertens, A. Divakaran, G. Friedland, and M. Hasegawa-Johns

ICSI Research Group

Audio and Multimedia

ICSI Publication Type

Article in conference proceedings