Query expansion techniques for a phrase-based melody retrieval system

The increasing availability of digital music has created a need for effective music retrieval methods. In music information retrieval (MIR) systems, proper query terms affect the retrieval performance signifintly. The performance of the systems can be improved by using query expansion techniques. In this paper, based on our previous work [9], we present query expansion techniques to solve the problems caused by the complex interaction of substitution, insertion and deletion errors. The proposed approach is compared with state of the art techniques and its effectiveness in melody retrieval is demonstrated. In addition, extensive experiments show its robustness against various kinds of query error.