No abstract

Advances in music retrieval research greatly depend on appropriate database resources and their meaningful organization. In this paper we describe the data collection efforts related to the design of query by humming (QBH) systems. We also provide a statistical analysis for categorizing the collected data, especially focusing on inter-subject variability issues. In total, 100 people participated in our experiment resulting in around 2000 humming samples drown from a predefined melody list consisting of 22 different well known music pieces, and over 500 samples of melodies that were chosen spontaneously by our subjects. These data will be made available for the research community. The data from each subject were compared to the expected melody features, and an objective measure was derived to quantify the statistical deviation from the baseline. The results showed that the uncertainty in the humming varies with respect to the melodies' musical structure and subjects' musical background. Such details are important for designing robust QBH systems.

No abstract

No abstract