期刊
SIGNAL PROCESSING
卷 92, 期 11, 页码 2723-2737出版社
ELSEVIER
DOI: 10.1016/j.sigpro.2012.04.023
关键词
Music genre; Texture; Image processing; Pattern recognition
资金
- The National Council for Scientific and Technological Development (CNPq) [301653/2011-9]
- CAPES [BEX 5779/11-1, 223/09-FCT595-2009]
- Araucaria Foundation [16767-424/2009]
- European Commission
- FP7 (Seventh Framework Programme)
- ICT-2011.1.5 Networked Media and Search Systems [287711]
- European Regional Development Fund through the Programme COMPETE
- National Funds through the Portuguese Foundation for Science and Technology [PTDC/EAT-MMU/112255/2009, PTDC/EIA-CCO/111050/2009]
- Fundação para a Ciência e a Tecnologia [PTDC/EAT-MMU/112255/2009, PTDC/EIA-CCO/111050/2009] Funding Source: FCT
In this paper we present an approach to music genre classification which converts an audio signal into spectrograms and extracts texture features from these time-frequency images which are then used for modeling music genres in a classification system. The texture features are based on Local Binary Pattern, a structural texture operator that has been successful in recent image classification research. Experiments are performed with two well-known datasets: the Latin Music Database (LMD), and the ISMIR 2004 dataset. The proposed approach takes into account some different zoning mechanisms to perform local feature extraction. Results obtained with and without local feature extraction are compared. We compare the performance of texture features with that of commonly used audio content based features (i.e. from the MARSYAS framework), and show that texture features always outperforms the audio content based features. We also compare our results with results from the literature. On the LMD, the performance of our approach reaches about 82.33%, above the best result obtained in the MIREX 2010 competition on that dataset. On the ISMIR 2004 database, the best result obtained is about 80.65%, i.e. below the best result on that dataset found in the literature. (c) 2012 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据