APSIPA Transactions on Signal and Information Processing > Vol 5 > Issue 1

Robust and efficient content-based music retrieval system

Yuan-Shan Lee, National Central University, Taiwan, Yen-Lin Chiang, National Central University, Taiwan, Pei-Rung Lin, National Central University, Taiwan, Chang-Hung Lin, National Central University, Taiwan, Tzu-Chiang Tai, Providence University, Taiwan, tctai717@gmail.com
 
Suggested Citation
Yuan-Shan Lee, Yen-Lin Chiang, Pei-Rung Lin, Chang-Hung Lin and Tzu-Chiang Tai (2016), "Robust and efficient content-based music retrieval system", APSIPA Transactions on Signal and Information Processing: Vol. 5: No. 1, e4. http://dx.doi.org/10.1017/ATSIP.2016.4

Publication Date: 28 Mar 2016
© 2016 Yuan-Shan Lee, Yen-Lin Chiang, Pei-Rung Lin, Chang-Hung Lin and Tzu-Chiang Tai
 
Subjects
 
Keywords
Query-by-singing, Music retrieval, Symbolic sequence, Pattern indexing, Information entropy
 

Share

Journal details

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 1295 times

In this article:
I. INTRODUCTION 
II. RELATED WORKS 
III. THE SYSTEM ARCHITECTURE OVERVIEW 
IV. MUSIC RETRIEVAL PROCESS 
V. THE STORAGE STRUCTURES AND THE SCORING MECHANISM OF THE DATABASE 
VI. EVALUATING THE PERFOMANCE BY EXPERIMENTS 
VII. CONCLUSION 

Abstract

This work proposes a query-by-singing (QBS) content-based music retrieval (CBMR) system that uses Approximate Karbunen–Loeve transform for noise reduction. The proposed QBS-CBMR system uses a music clip as a search key. First, a 51-dimensional matrix containing 39-Mel-frequency cepstral coefficients (MFCCs) features and 12-Chroma features are extracted from an input music clip. Next, adapted symbolic aggregate approximation (adapted SAX) is used to transform each dimension of features into a symbolic sequence. Each symbolic sequence corresponding to each dimension of MFCCs is then converted into a structure called advanced fast pattern index (AFPI) tree. The similarity between the query music clip and the songs in the database is evaluated by calculating a partial score for each AFPI tree. The final score is obtained by calculating the weighted sum of all partial scores, where the weighting of each partial score is determined by its entropy. Experimental results show that the proposed music retrieval system performs robustly and accurately with the entropy weighting mechanism.

DOI:10.1017/ATSIP.2016.4