Kaare Brandt Petersen

Università degli Studi di Trento, Trient, Trentino-Alto Adige, Italy

Are you Kaare Brandt Petersen?

Claim your profile

Publications (13)6.89 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Feature extraction and dimensionality reduction are important tasks in many fields of science dealing with signal processing and analysis. The relevance of these techniques is increasing as current sensory devices are developed with ever higher resolution, and problems involving multimodal data sources become more common. A plethora of feature extraction methods are available in the literature collectively grouped under the field of Multivariate Analysis (MVA). This paper provides a uniform treatment of several methods: Principal Component Analysis (PCA), Partial Least Squares (PLS), Canonical Correlation Analysis (CCA) and Orthonormalized PLS (OPLS), as well as their non-linear extensions derived by means of the theory of reproducing kernel Hilbert spaces. We also review their connections to other methods for classification and statistical dependence estimation, and introduce some recent developments to deal with the extreme cases of large-scale and low-sized problems. To illustrate the wide applicability of these methods in both classification and regression problems, we analyze their performance in a benchmark of publicly available data sets, and pay special attention to specific real applications involving audio processing for music genre prediction and hyperspectral satellite images for Earth and climate monitoring.
    IEEE Signal Processing Magazine 10/2013; 30(4). · 3.37 Impact Factor
  • Jerónimo Arenas-García, Kaare Brandt Petersen
    11/2009: pages 327 - 352; , ISBN: 9780470748992
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Nowadays there is an increasing interest in developing methods for building music recommendation systems. In order to get a satisfactory performance from such a system, one needs to incorporate as much information about songs similarity as possible; however, how to do so is not obvious. In this paper, we build on the ideas of the Probabilistic Latent Semantic Analysis (PLSA) that has been successfully used in the document retrieval community. Under this probabilistic framework, any song will be projected into a relatively low dimensional space of "latent semantics", in such a way that that all observed similarities can be satisfactorily explained using the latent semantics. Additionally, this approach significantly simplifies the song retrieval phase, leading to a more practical system implementation. The suitability of the PLSA model for representing music structure is studied in a simplified scenario consisting of 10.000 songs and two similarity measures among them. The results suggest that the PLSA model is a useful framework to combine different sources of information, and provides a reasonable space for song representation.
    Machine Learning for Signal Processing, 2007 IEEE Workshop on; 09/2007
  • [Show abstract] [Hide abstract]
    ABSTRACT: Slow convergence is observed in the EM algorithm for linear state-space models. We propose to circumvent the problem by applying any off-the-shelf quasi-Newton-type optimizer, which operates on the gradient of the log-likelihood function. Such an algorithm is a practical alternative due to the fact that the exact gradient of the log-likelihood function can be computed by recycling components of the expectation-maximization (EM) algorithm. We demonstrate the efficiency of the proposed method in three relevant instances of the linear state-space model. In high signal-to-noise ratios, where EM is particularly prone to converge slowly, we show that gradient-based learning results in a sizable reduction of computation time.
    Neural Computation 01/2007; 19:1097-1111. · 1.76 Impact Factor
  • Source
    Ole Winther, Kaare Brandt Petersen
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we present an empirical Bayesian framework for independent component analysis. The framework provides estimates of the sources, the mixing matrix and the noise parameters, and is flexible with respect to choice of source prior and the number of sources and sensors. Inside the engine of the method are two mean field techniques—the variational Bayes and the expectation consistent framework—and the cost function relating to these methods are optimized using the adaptive overrelaxed expectation maximization (EM) algorithm and the easy gradient recipe. The entire framework, implemented in a Matlab toolbox, is demonstrated for non-negative decompositions and compared with non-negative matrix factorization.
    Digital Signal Processing. 01/2007;
  • Source
    Ole Winther, Kaare Brandt Petersen
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we present an empirical Bayes method for flexible and efficient independent component analysis (ICA). The method is flexible with respect to choice of source prior, dimensionality and constraints of the mixing matrix (unconstrained or non-negativity), and structure of the noise covariance matrix. Parameter optimization is handled by variants of the expectation maximization (EM) algorithm: overrelaxed adaptive EM and the easy gradient recipe. These retain the simplicity of EM while converging faster. The required expectations over the source posterior, the sufficient statistics, are estimated with mean field methods: variational and the expectation consistent (EC) framework. We describe the derivation of the EC framework for ICA in detail and give empirical results demonstrating the improved performance. The paper is accompanied by the publicly available Matlab toolbox icaMF.
    Neurocomputing. 01/2007;
  • Source
    Sigurdur Sigurdsson, Kaare Brandt Petersen, Tue Lehn-Schiøler
    [Show abstract] [Hide abstract]
    ABSTRACT: In large MP3 databases, files are typically generated with different parameter settings, i.e., bit rate and sampling rates. This is of concern for MIR applications, as encoding dif- ference can potentially confound meta-data estimation and similarity evaluation. In this paper we will discuss the in- fluence of MP3 coding for the Mel frequency cepstral coe- ficients (MFCCs). The main result is that the widely used subset of the MFCCs is robust at bit rates equal or higher than 128 kbits/s, for the implementations we have investi- gated. However, for lower bit rates, e.g., 64 kbits/s, the im- plementation of the Mel filter bank becomes an issue.
    ISMIR 2006, 7th International Conference on Music Information Retrieval, Victoria, Canada, 8-12 October 2006, Proceedings; 01/2006
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This demonstration illustrates how the methods developed in the MIR community can be used to provide real-time feedback to music users. By creating a genre classifier plug- in for a popular media player we present users with rele- vant information as they play their songs. The plug-in can furthermore be used as a data collection platform. After informed consent from a selected set of users the plug-in will report on music consumption behavior back to a central server.
    ISMIR 2006, 7th International Conference on Music Information Retrieval, Victoria, Canada, 8-12 October 2006, Proceedings; 01/2006
  • Source
    Jerónimo Arenas-García, Kaare Brandt Petersen, Lars Kai Hansen
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we are presenting a novel multivariate analysis method. Our scheme is based on a novel kernel orthonormalized partial least squares (PLS) variant for feature extraction, imposing sparsity constrains in the so lution to improve scalabil- ity. The algorithm is tested on a benchmark of UCI data sets, and on the analysis of integrated short-time music features for genre predicti on. The upshot is that the method has strong expressive power even with rather few features, is clearly outperforming the ordinary kernel PLS, and therefore is an appealing method for feature extraction of labelled data.
    Advances in Neural Information Processing Systems 19, Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 4-7, 2006; 01/2006
  • Kaare Brandt Petersen, Ole Winther, Lars Kai Hansen
    [Show abstract] [Hide abstract]
    ABSTRACT: We analyze convergence of the expectation maximization (EM) and variational Bayes EM (VBEM) schemes for parameter estimation in noisy linear models. The analysis shows that both schemes are inefficient in the low-noise limit. The linear model with additive noise includes as special cases independent component analysis, probabilistic principal component analysis, factor analysis, and Kalman filtering. Hence, the results are relevant for many practical applications.
    Neural Computation 10/2005; 17(9):1921-1926. · 1.76 Impact Factor
  • Source
    Lars Kai Hansen, Kaare Brandt Petersen
    [Show abstract] [Hide abstract]
    ABSTRACT: Separation of monaural linear mixtures of 'white' source signals is fundamentally ill-posed. In some situations it is not possible to find the mixing coefficients for the full 'blind' problem. If the mixing coefficients are known, the structure of the source prior distribution de- termines the source reconstruction error. If the prior is strongly multi-modal source reconstruction is possible with low error, while source signals from the typical 'long tailed' distributions used in many ICA settings can not be reconstructed. We provide a qualitative dis- cussion of the limits of monaural blind separation of white noise signals and give a set of no go cases, fi- nally, we use a so-called Mean Field approach to derive an algorithm for ICA of noisy monaural mixtures with a bi-modal source prior and demonstrate that low error source reconstructions are possible when the bi-modal source is close to binary. This is the first demonstration of blind source separation in noisy monaural mixtures without invoking temporal correlation information.
    01/2003;
  • Source
    Kaare Brandt Petersen, Jiucang Hao, Te-Won Lee
    [Show abstract] [Hide abstract]
    ABSTRACT: We investigate the properties of the generative and filtering approach to over- complete representations. A Mixture of Gaussian (MoG) density model is used to derive estimation rules for an energy based model, which estimate the filtering matrix, as well as a generative model which estimate the mixing matrix. In the light of two different source priors - a spherical MoG and an independent MoG - we reveal how those two seemingly different approaches can be understood. We also provide a new zero noise case which enables a closer comparison of the generative model to the energy based model.
  • Source
    Anders Meng, Kaare Brandt Petersen, Lars Kai
    [Show abstract] [Hide abstract]
    ABSTRACT: There is an increasing interest in customizable methods for organizing music col- lections. Relevant music characterization can be obtained from short-time fea- tures, but it is not obvious how to combine them to get useful information. First, the relevant information might not be evident at the short-t ime level, and these features have to be combined at a larger temporal level into a new feature vector in order to capture the relevant information. Second, we need to learn a model for the new features that generalizes well to new data. In thi s contribution, we will study how multivariate analysis (MVA) and kernel methods can be of great help in this task. More precisely, we will present two modifie d versions of a MVA method known as Orthonormalized Partial Least Squares (OPLS), one of them being a kernel extension, that are well-suited for discover ing relevant dynamics in large music collections. The performance of both schemes will be illustrated in a music genre classification task.

Publication Stats

85 Citations
6.89 Total Impact Points

Institutions

  • 2009
    • Università degli Studi di Trento
      Trient, Trentino-Alto Adige, Italy
  • 2005–2007
    • Technical University of Denmark
      • Department of Informatics and Mathematical Modelling
      Copenhagen, Capital Region, Denmark