A Survey on Query-by-Example based Music Information Retrieval

Abstract

ABSTRACTsearch in huge musical datasets using a query provided as a fragment of desired song while there exists no extra information is a particular concern in content-based music information retrieval (MIR), defined as query-by-example (QBE). A number of QBE based MIR systems have evolved in recent years, which search a desired song without any manual of its originality, such as title, composer, singer or etc., and return a list of songs ranked in descending order according to the similarity with the given query recorded by user on TV, in gym or so on. Although, too much attention has been paid to this topic by researchers and developers in several communities, such as information retrieval, data mining or multimedia browsing engines, but it still suffers from no existing a unique definition on structure, aim, similarity, performance and also output results. This paper focuses on providing a brief overview of available QBE based MIR systems to manifest variety, opportunities and challenges in this area.