The MUSART Testbed for Query-by-Humming Evaluation
Open Access
- 1 June 2004
- journal article
- Published by MIT Press in Computer Music Journal
- Vol. 28 (2) , 34-48
- https://doi.org/10.1162/014892604323112239
Abstract
Evaluating music information retrieval systems is acknowledged to be a difficult problem. We have created a database and a software testbed for the systematic evaluation of various query-by-humming (QBH) search systems. As might be expected, different queries and different databases lead to w ide variations in observed search precision. "Natural" queries from two sources led to lower performance than that typically reported in the QBH literature. These results point out the importance of careful measurement and objective comparisons to study retrieval algorithms. This study compares search algorithms based on note-interval matching with dynamic programming, fixed-frame melodic contour matching with dynamic time warping, and a hidden Markov model. An examination of scaling trends is encouraging: precision falls off very slowly as the database size increases. This trend is simple to compute and could be useful to predict performance on larger databases.Keywords
This publication has 3 references indexed in Scilit:
- Name that tune: A pilot study in finding a melody from a sung queryJournal of the American Society for Information Science and Technology, 2003
- A computationally efficient multipitch analysis modelIEEE Transactions on Speech and Audio Processing, 2000
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989