Click here for full text:
Toward Evaluation Techniques for Music Similarity
Logan, Beth; Ellis, Daniel P.W.; Berenzweig, Adam
HPL-2003-159
Keyword(s): music information retrieval; multimedia indexing; music analysis; information retrieval
Abstract: We describe and discuss our recent work developing a database, methodology and ground truth for the evaluation of automatic techniques for music similarity. Our database consists of acoustic and textual 'Web-mined' data covering 400 popular artists. Of note is our technique of sharing acoustic features rather than raw audio to avoid copyright problems. Our evaluation methodology allows any data source to be regarded as ground truth and can highlight which measure forms the best collective ground truth. We additionally describe an evaluation methodology that is useful for data collected from people in the form of a survey about music similarity. We have successfully used our database and techniques to evaluate a number of music similarity algorithms. Notes: Published in and presented at SIGIR 2003: Workshop on the Evaluation of Music Information Retrieval Systems, 1 August 2003, Toronto, Canada
10 Pages
Back to Index
| 
printable version
