Dynamic Chord Analysis for Symbolic Music

In this paper, we present a new method for chord recognition from symbolic music. This method builds a graph of all possible chords and selects the best path in this graph. A rulebased approach is adopted to enumerate chord candidates from groups of notes by considering compatible chords and compatible keys. The distance proposed by Lerdahl is then used to compute costs between different chord candidates. Dynamic programming is also involved to select the best path among chord candidates. Experiments are performed on a MIDI song database, divided in different music styles. Then the proposed system is compared to the Melisma Music Analyzer software proposed by Temperley. Results show that our method has a comparable efficiency and provides not only the root of the chord, but also its mode (major or minor). The proposed system is still open and is able to support more chord types if correct rules to handle them are specified.

[1]  François Pachet,et al.  Automatic X Traditional Descriptor Extraction: the Case of Chord Recognition , 2005, ISMIR.

[2]  R. Bellman.  Dynamic programming. , 1957, Science.

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

[4]  Juan Pablo Bello,et al.  A Robust Mid-Level Representation for Harmonic Content in Music Signals , 2005, ISMIR.

[5]  D. Temperley.  The Cognition of Basic Musical Structures , 2001 .

[6]  Malcolm Slaney,et al.  Acoustic Chord Transcription and Key Extraction From Audio Using Key-Dependent HMMs Trained on Synthesized Audio , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[7]  Fred Lerdahl,et al.  Tonal Pitch Space , 2001 .

[8]  Jean-François Paiement,et al.  A Probabilistic Model for Chord Progressions , 2005, ISMIR.

[9]  Daniel P. W. Ellis,et al.  Chord segmentation and recognition using EM-trained hidden markov models , 2003, ISMIR.

[10]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[11]  Elaine Chew,et al.  The Spiral Array: An Algorithm for Determining Key Boundaries , 2002, ICMAI.

[12]  José Manuel Iñesta Quereda,et al.  Harmonic, Melodic, and Functional Automatic Analysis , 2007, ICMC.

[13]  Juan Pablo Bello,et al.  Audio-Based Cover Song Retrieval Using Approximate Chord Sequences: Testing Shifts, Gaps, Swaps and Beats , 2007, ISMIR.

[14]  Julien Allali,et al.  Improvements of Alignment Algorithms for Polyphonic Music Retrieval , 2008 .

[15]  Geoffroy Peeters,et al.  Large-Scale Study of Chord Estimation Algorithms Based on Chroma Representation and HMM , 2007, 2007 International Workshop on Content-Based Multimedia Indexing.