Dynamic Nonparametric Bayesian Models for Analysis of Music

The dynamic hierarchical Dirichlet process (dHDP) is developed to model complex sequential data, with a focus on audio signals from music. The music is represented in terms of a sequence of discrete observations, and the sequence is modeled using a hidden Markov model (HMM) with time-evolving parameters. The dHDP imposes the belief that observations that are temporally proximate are more likely to be drawn from HMMs with similar parameters, while also allowing for “innovation” associated with abrupt changes in the music texture. The sharing mechanisms of the time-evolving model are derived, and for inference a relatively simple Markov chain Monte Carlo sampler is developed. Segmentation of a given musical piece is constituted via the model inference. Detailed examples are presented on several pieces, with comparisons to other models. The dHDP results are also compared with a conventional music-theoretic analysis. All the supplemental materials used by this paper are available online.

[1]  D. Dunson,et al.  The local Dirichlet process , 2011, Annals of the Institute of Statistical Mathematics.

[2]  Arnaud Doucet,et al.  Bayesian Inference for Linear Dynamic Models With Dirichlet Process Mixtures , 2007, IEEE Transactions on Signal Processing.

[3]  Lancelot F. James.  Discussion of Nested Dirichlet Process paper by Rodriguez, Dunson and Gelfand , 2008 .

[4]  Michael I. Jordan,et al.  An HDP-HMM for systems with state persistence , 2008, ICML '08.

[5]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[6]  David A. Forsyth,et al.  Matching Words and Pictures , 2003, J. Mach. Learn. Res..

[7]  A. Raftery,et al.  How Many Iterations in the Gibbs Sampler , 1991 .

[8]  Christopher Raphael,et al.  Automatic Segmentation of Acoustic Musical Signals Using Hidden Markov Models , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[10]  Mario Medvedovic,et al.  Bayesian infinite mixture model based clustering of gene expression profiles , 2002, Bioinform..

[11]  Michael I. Jordan,et al.  Variational methods for the Dirichlet process , 2004, ICML.

[12]  John D. Lafferty,et al.  Dynamic topic models , 2006, ICML.

[13]  Jimeng Sun,et al.  Dynamic Mixture Models for Multiple Time-Series , 2007, IJCAI.

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

[15]  J. E. Griffin,et al.  Order-Based Dependent Dirichlet Processes , 2006 .

[16]  Enrique ter Horst,et al.  Bayesian dynamic density estimation , 2008 .

[17]  David B. Dunson,et al.  Multi-task learning for sequential data via iHMMs and the nested Dirichlet process , 2007, ICML '07.

[18]  H. Ishwaran,et al.  Exact and approximate sum representations for the Dirichlet process , 2002 .

[19]  A. Gelfand,et al.  The Nested Dirichlet Process , 2008 .

[20]  Beth Logan,et al.  Mel Frequency Cepstral Coefficients for Music Modeling , 2000, ISMIR.

[21]  David B. Dunson,et al.  Multi-Task Learning for Analyzing and Sorting Large Databases of Sequential Data , 2008, IEEE Transactions on Signal Processing.

[22]  Lancelot F. James,et al.  Gibbs Sampling Methods for Stick-Breaking Priors , 2001 .

[23]  D. Temperley.  Music and probability , 2006 .

[24]  S. MacEachern,et al.  A semiparametric Bayesian model for randomised block designs , 1996 .

[25]  John Geweke,et al.  Evaluating the accuracy of sampling-based approaches to the calculation of posterior moments , 1991 .

[26]  Jean-François Paiement,et al.  A Generative Model for Rhythms , 2007, NIPS 2007.

[27]  J. Sethuraman.  A CONSTRUCTIVE DEFINITION OF DIRICHLET PRIORS , 1991 .

[28]  François Pachet,et al.  The influence of polyphony on the dynamical modelling of musical timbre , 2007, Pattern Recognit. Lett..

[29]  David Temperley,et al.  A Probabilistic Model of Melody Perception , 2008, ISMIR.

[30]  D. Dunson.  Bayesian dynamic modeling of latent trait distributions. , 2006, Biostatistics.

[31]  Søren Holdt Jensen,et al.  Evaluation of MFCC estimation techniques for music similarity , 2006, 2006 14th European Signal Processing Conference.

[32]  Carl E. Rasmussen,et al.  Factorial Hidden Markov Models , 1997 .

[33]  Lawrence Carin,et al.  Music Analysis Using Hidden Markov Mixture Models , 2007, IEEE Transactions on Signal Processing.

[34]  T. Ferguson.  A Bayesian Analysis of Some Nonparametric Problems , 1973 .

[35]  D. Blackwell,et al.  Ferguson Distributions Via Polya Urn Schemes , 1973 .

[36]  M. Escobar,et al.  Bayesian Density Estimation and Inference Using Mixtures , 1995 .

[37]  Bstract,et al.  DYNAMIC DENSITY ESTIMATION WITH FINANCIAL APPLICATIONS , 2006 .

[38]  Arnaud Doucet,et al.  Generalized Polya Urn for Time-varying Dirichlet Process Mixtures , 2007, UAI.

[39]  Kai Lienemann,et al.  Automatic Detection of Song Changes in Music Mixes Using Stochastic Models , 2006, 18th International Conference on Pattern Recognition (ICPR'06).