Audio information mining pragmatic review, outlook and a universal open architecture

Duncan, PJ; Mohammed, DY; Li, FF

Abstract

There is an immense amount of audio data available currently whose content is unspecified and the problem of classification and generation of metadata poses a significant and challenging research problem. We present a review of past and current work in this field; specifically in the three principal areas of segmentation, feature extraction and classification and give an overview and critical appraisal of techniques currently in use. One of the major impediments to progress in the field has been specialism and the inability of classifiers to generalize and we propose a nonexclusive generalized open architecture framework for classification of audio data which will accommodate third party plugins and work with multi-dimensional feature/descriptor space as input.

Citation

Duncan, P., Mohammed, D., & Li, F. (2014, April). Audio information mining pragmatic review, outlook and a universal open architecture. Presented at Audio Engineering Society 136th Convention, Berlin

• Presentation Conference Type: Other
• Conference Name: Audio Engineering Society 136th Convention
• Conference Location: Berlin
• Start Date: Apr 26, 2014
• End Date: Apr 29, 2014
• Acceptance Date: Mar 19, 2023
• Publication Date: Apr 25, 2014
• Deposit Date: Jul 3, 2015
• Publisher: Audio Engineering Society
• Publisher URL: http://www.aes.org/e-lib/browse.cfm?elib=17222
• Related Public URLs: http://www.aes.org/
• Additional Information: Event Type : Conference; Funders : Iraqi Government sponsored Ph.D