MidiFind: Similarity Search and Popularity Mining in Large MIDI Databases

While there are perhaps millions of MIDI files available over the Internet, it is difficult to find performances of a particular piece because well labeled metadata and indexes are unavailable. We address the particular problem of finding performances of compositions for piano, which is different from often-studied problems of Query-by-Humming and Music Fingerprinting. Our MidiFind system is designed to search a million MIDI files with high precision and recall. By using a hybrid search strategy, it runs more than 1000 times faster than naive competitors, and by using a combination of bag-of-words and enhanced Levenshtein distance methods for similarity, our system achieves a precision of 99.5 % and recall of 89.8 %.

[1]  Gerhard Widmer,et al.  YQX Plays Chopin , 2009, AI Mag..

[2]  Ton Kalker,et al.  A Highly Robust Audio Fingerprinting System , 2002, ISMIR.

[3]  Martha Larson,et al.  SVM Classification Using Sequences of Phonemes and Syllables , 2002, PKDD.

[4]  Bernhard Schölkopf,et al.  Kernel Principal Component Analysis , 1997, ICANN.

[5]  Jan Komorowski,et al.  Principles of Data Mining and Knowledge Discovery , 2001, Lecture Notes in Computer Science.

[6]  Jonathon Shlens,et al.  A Tutorial on Principal Component Analysis , 2014, ArXiv.

[7]  Roger B. Dannenberg,et al.  Melody Matching Directly From Audio , 2001 .

[8]  Kevin W. Boyack,et al.  OpenOrd: an open-source toolbox for large graph layout , 2011, Electronic Imaging.

[9]  Jyh-Shing Roger Jang,et al.  Hierarchical filtering method for content-based music retrieval via acoustic input , 2001, MULTIMEDIA '01.

[10]  C. Krumhansl.  Cognitive Foundations of Musical Pitch , 1990 .

[11]  Mathieu Bastian,et al.  Gephi: An Open Source Software for Exploring and Manipulating Networks , 2009, ICWSM.

[12]  Pavel Zezula,et al.  M-tree: An Efficient Access Method for Similarity Search in Metric Spaces , 1997, VLDB.

[13]  Brian Christopher Smith,et al.  Query by humming: musical information retrieval in an audio database , 1995, MULTIMEDIA '95.

[14]  Justin Zobel,et al.  Manipulation of music for melody matching , 1998, MULTIMEDIA '98.

[15]  Piotr Indyk,et al.  Similarity Search in High Dimensions via Hashing , 1999, VLDB.

[16]  Hui Ding,et al.  Querying and mining of time series data: experimental comparison of representations and distance measures , 2008, Proc. VLDB Endow..

[17]  Ian H. Witten,et al.  The New Zealand Digital Library MELody inDEX , 1997, D Lib Mag..

[18]  Daniel P. W. Ellis,et al.  The Echo Nest Musical Fingerprint , 2010 .

[19]  Gerhard Widmer,et al.  Playing Mozart by Analogy: Learning Multi-level Timing and Dynamics Strategies , 2003 .

[20]  Dimitrios Gunopulos,et al.  Embedding-based subsequence matching in time-series databases , 2011, TODS.

[21]  Justin Zobel,et al.  Melodic matching techniques for large music databases , 1999, MULTIMEDIA '99.

[22]  George Tzanetakis,et al.  A comparative evaluation of search techniques for query-by-humming using the MUSART testbed , 2007 .

[24]  Nello Cristianini,et al.  Classification using String Kernels , 2000 .

[25]  Dennis Shasha,et al.  Warping indexes with envelope transforms for query by humming , 2003, SIGMOD '03.