원문정보
초록
영어
With the explosive growth of digital music, content-based music information retrieval especially query by humming / singing have been attracting more and more attention and are becoming popular research topics over the past decade. Although query by humming / singing can provide natural and intuitive way to search music, retrieval system still confronts many issues such as key modulation, tempo change, note insertion, deletion or substitution which are caused by users and query transcription respectively. In this paper, we propose a novel approach based on fault tolerance and recursive segmentation to solve above problems. Music melodies in database are represented with specified manner and indexed using inverted index method. Query melody is segmented into phrases recursively with musical dictionary firstly. Then improved edit distance, pitch deviation and overall bias are employed to measure the similarity between phrases and indexed entries. Experimental results reveal that proposed approach can achieve high recall for music retrieval.
목차
1. Introduction
2. Index construction
2.1. Melody representation
2.2. Musical dictionary
2.3. Melody partition
3. Proposed QBH approach
3.1. Query transcription
3.2. Similarity measurement
3.3. Fault tolerance mechanism
3.4. Recursive segmentation
4. Experiments
4.1. Dataset
4.2. Environment
4.3. Performance
5. Conclusions
6. Acknowledgments
7. References