Tempo- and Transposition-invariant Identification of Piece and Score Position

We present an algorithm that, given a very small snippet of an audio performance and a database of musical scores, quickly identifies the piece and the position in the score. The algorithm is both tempo- and transposition-invariant. We approach the problem by extending an existing tempoinvariant symbolic fingerprinting method, replacing the absolute pitch information in the fingerprints with a relative representation. Not surprisingly, this leads to a big decrease in the discriminative power of the fingerprints. To overcome this problem, we propose an additional verification step to filter out the introduced noise. Finally, we present a simple tracking algorithm that increases the retrieval precision for longer queries. Experiments show that both modifications improve the results, and make the new algorithm usable for a wide range of applications.

[1]  Gerhard Widmer,et al.  Fast Identification of Piece and Score Position via Symbolic Fingerprinting , 2012, ISMIR.

[2]  S. Roweis,et al.  ASTROMETRY.NET: BLIND ASTROMETRIC CALIBRATION OF ARBITRARY ASTRONOMICAL IMAGES , 2009, 0910.2233.

[3]  Emilia Gómez,et al.  Audio Cover Song Identification and Similarity: Background, Approaches, Evaluation, and Beyond , 2010, Advances in Music Information Retrieval.

[4]  Gerhard Widmer,et al.  SIARCT-CFP: Improving Precision and the Discovery of Inexact Musical Patterns in Point-Set Representations , 2013, ISMIR.

[5]  Markus Schedl,et al.  Polyphonic piano note transcription with recurrent neural networks , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Gerhard Widmer,et al.  Discovering simple rules in complex data: A meta-learning algorithm and some surprising musical discoveries , 2003, Artif. Intell..

[7]  Simon Dixon,et al.  Automatic Extraction of Tempo and Beat From Expressive Performances , 2001 .

[8]  Meinard Müller,et al.  Audio Matching via Chroma-Based Statistical Features , 2005, ISMIR.

[9]  Avery Wang,et al.  An Industrial Strength Audio Search Algorithm , 2003, ISMIR.

[10]  Pedro Cano,et al.  A review of algorithms for audio fingerprinting , 2002, 2002 IEEE Workshop on Multimedia Signal Processing..

[11]  Meinard Müller,et al.  Efficient Index-Based Audio Matching , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[12]  Gerhard Widmer,et al.  Quad-Based Audio Fingerprinting Robust to Time and Frequency Scaling , 2014, DAFx.

[13]  Gerhard Widmer,et al.  The Magaloff Project: An Interim Report , 2010 .