EXTRACTING GROUND TRUTH INFORMATION FROM MIDI FILES:

MIDI files abound and provide a bounty of information for music informatics. We enumerate the types of information available in MIDI files and describe the steps necessary for utilizing them. We also quantify the reliability of this data by comparing it to human-annotated ground truth. The results suggest that developing better methods to leverage information present in MIDI files will facilitate the creation of MIDI-derived ground truth for audio content-based MIR.

[1]  Daniel P. W. Ellis,et al.  Optimizing DTW-based audio-to-MIDI alignment and matching , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Daniel P. W. Ellis,et al.  Pruning subsequence search with attention-based embedding , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Daniel P. W. Ellis,et al.  Large-Scale Content-Based Matching of MIDI and Audio Files , 2015, ISMIR.

[4]  Mark D. Plumbley,et al.  Score-Informed Source Separation for Musical Audio Recordings: An overview , 2014, IEEE Signal Processing Magazine.

[5]  Florian Krebs,et al.  A Multi-model Approach to Beat Tracking Considering Heterogeneous Music Styles , 2014, ISMIR.

[6]  Daniel P. W. Ellis,et al.  MIR_EVAL: A Transparent Implementation of Common MIR Metrics , 2014, ISMIR.

[7]  S. Dixon,et al.  MIREX 2019: VAMP PLUGINS FROM THE CENTRE FOR DIGITAL MUSIC , 2013 .

[8]  Meinard Müller,et al.  Towards Cross-Version Harmonic Analysis of Music , 2012, IEEE Transactions on Multimedia.

[9]  Simon Dixon,et al.  A Corpus-based Study of Rhythm Patterns , 2012, ISMIR.

[10]  Christopher Ariza,et al.  Feature Extraction and Machine Learning on Symbolic Music using the music21 Toolkit , 2011, ISMIR.

[11]  Thierry Bertin-Mahieux,et al.  The Million Song Dataset , 2011, ISMIR.

[12]  Christopher Ariza,et al.  Music21: A Toolkit for Computer-Aided Musicology and Symbolic Music Data , 2010, ISMIR.

[13]  Orberto,et al.  Evaluation Methods for Musical Audio Beat Tracking Algorithms , 2009 .

[14]  David Rizo,et al.  Mining Digital Music Score Collections: Melody Extraction and Genre Recognition , 2008 .

[15]  J. Stephen Downie,et al.  The music information retrieval evaluation exchange (2005-2007): A window into music information retrieval research , 2008 .

[16]  Daniel Müllensiefen,et al.  Bayesian Model Selection for Harmonic Labelling , 2007 .

[17]  Mark Sandler,et al.  Signal Processing Parameters for Tonality Estimation , 2007 .

[18]  Ichiro Fujinaga,et al.  jSymbolic: A Feature Extractor for MIDI Files , 2006, ICMC.

[19]  Mark B. Sandler,et al.  A tutorial on onset detection in music signals , 2005, IEEE Transactions on Speech and Audio Processing.

[20]  Daniel P. W. Ellis,et al.  Ground-truth transcriptions of real music from force-aligned MIDI syntheses , 2003, ISMIR.

[21]  George Tzanetakis,et al.  Polyphonic audio matching and alignment for music retrieval , 2003, 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684).

[22]  Michael Good,et al.  MusicXML for notation and analysis , 2001 .

[23]  Chi Lap Yip,et al.  Selection of melody lines for music databases , 2000, Proceedings 24th Annual International Computer Software and Applications Conference. COMPSAC2000.

[24]  F. Richard Moore,et al.  The Dysfunctions of MIDI , 1988, ICMC.