Abstract:
Singing voice detection for musical structural analysis is an important but difficult area, which makes a great contribution to music segment. This paper proposes an effi...Show MoreMetadata
Abstract:
Singing voice detection for musical structural analysis is an important but difficult area, which makes a great contribution to music segment. This paper proposes an efficient singing voice detection system by using beat tracking technique and SVM classification. We do the experiment using beat as a unit of classification instead of frame. Compared with a conventional frame-based classification, the run time of beat-based classification system reduces about 20%, and achieve 72.8% of precision. Meanwhile, in practice, the beat-based classification system achieves about 88.3% of precision.
Published in: 2015 IEEE/ACIS 14th International Conference on Computer and Information Science (ICIS)
Date of Conference: 28 June 2015 - 01 July 2015
Date Added to IEEE Xplore: 27 July 2015
Electronic ISBN:978-1-4799-8679-8