The Influence of Chord Duration Modeling on Chord and Local Key Extraction

In this paper, we investigate the effect of different types of chord duration modeling on the performance of a simultaneous chord and local key extraction system. Two hypotheses are examined, (1) whether the introduction of multiple states per key-chord combination makes any difference as it changes the prior duration from a geometric distribution to a negative binomial distribution, and (2) whether making the prior mean duration of a key-chord combination a function of the chord has a positive effect. We found that the introduction of multiple states per key-chord has no influence on neither key nor chord extraction performance, but making the mean duration a function of the chord interpreted in its key leads to an increase in the key estimation capabilities.

[1]  Maurizio Omologo,et al.  Use of Hidden Markov Models and Factored Language Models for Automatic Chord Recognition , 2009, ISMIR.

[2]  José Manuel Iñesta Quereda,et al.  Genre classification using chords and stochastic language models , 2009, Connect. Sci..

[3]  Ron J. Weiss,et al.  Exploring common variations in state of the art chord recognition systems , 2010 .

[4]  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.

[5]  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.

[6]  Simon Dixon,et al.  Simultaneous Estimation of Chords and Musical Context From Audio , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[7]  Laurent Oudre,et al.  Concurrent Estimation of Chords and Keys from Audio , 2010, ISMIR.

[8]  Hermann Ney,et al.  Improved backing-off for M-gram language modeling , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[9]  Mark B. Sandler,et al.  Influences of Signal Processing, Tone Profiles, and Chord Progressions on a Model for Estimating the Musical Key from Audio , 2009, Computer Music Journal.

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

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

[12]  Jean-Pierre Martens,et al.  A novel chroma representation of polyphonic music based on multiple pitch tracking techniques , 2008, ACM Multimedia.

[13]  Shigeki Sagayama,et al.  HMM-based approach for automatic chord detection using refined acoustic features , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[14]  Robert O. Gjerdingen,et al.  The Cognition of Basic Musical Structures , 2004 .

[15]  鐘期 坂本,et al.  Tonal Pitch Space を用いた楽曲の和声解析 , 2009 .

[16]  Takuya Fujishima,et al.  Realtime Chord Recognition of Musical Sound: a System Using Common Lisp Music , 1999, ICMC.