Index of /~echew/papers/MIR2004

 Name                    Last modified      Size  Description
 Parent Directory                             -   
 p041-unal.pdf           20-Aug-2004 09:15  271K  
 reference.txt           20-Aug-2004 09:18  431   

In this directory is the PDF file for a paper titled

"A Statistical Approach to Retrieval under User-dependent
Uncertainty in Query-by-Humming Systems"
by E. Unal, S.S. Narayanan and E. Chew
(unal@usc.edu, shri@sipi.usc.edu, echew@usc.edu)

The paper will be presented at the 
6th ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR 2004)
in conjunction with the 12th Annual ACM International Conference on Multimedia
New York, New York.  October 15-16, 2004.

The paper is published in the
Multimedia Information Retrieval Workshop Proceedings
Click on reference.txt for the BibTeX reference.

The project website is located at
http://sail.usc.edu/music

The workshop website is at 
http://www.liacs.nl/~mir

The conference website is at
http://www.acm.org/sigmm/mm2004

THE COMPLETE PAPER, text with figures, can be viewed as a PDF document.
Click on MIR03_unal.pdf if you wish to view the paper in PDF format.

--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--,--'--

"A Statistical Approach to Retrieval under User-dependent
Uncertainty in Query-by-Humming Systems"
by E. Unal, S.S. Narayanan and E. Chew
(unal@usc.edu, shri@sipi.usc.edu, echew@usc.edu)

ABSTRACT: Robustly addressing uncertainty in query formulation and
search is one of the most challenging problems in multimedia
information retrieval (MIR) systems. In this paper, a statistical
approach to the problem of retrieval under the effect of uncertainty
in Query by Humming (QBH) systems is presented.  Direct transcription
of audio to pitch and duration symbols is performed. From the
transcribed data vector, finger prints that carry a fixed length of
information from characteristic local points of the hummed melody are
extracted. Instead of employing the humming input as a whole,
extracted characteristic information packages are used for search
through the database. The distance for each finger print to the
original melodies in the database is calculated and converted to
probabilistic similarity measures.  Melodies with the highest
similarity measures are returned to the user as the most likely query
result. This algorithm is tested with manually annotated data
comprising 250 humming samples in conjunction with a database of 200
pre-processed midi files.  Retrieval accuracy of 94 percent is
demonstrated for the samples of subjects that have some musical
training/background compared to 72 percent accuracy achieved for the
samples of non-trained subjects. Results also show that extracting
finger prints with respect to characteristic local points of the
hummed tune is an effective and robust way for search and retrieval
under the effect of uncertainty.