Results 1  10
of
29
Semisupervised linear spectral unmixing using a hierarchical Bayesian model for hyperspectral imagery,” IRIT/ENSEEIHT/TeSA
, 2007
"... Abstract—This paper proposes a hierarchical Bayesian model that can be used for semisupervised hyperspectral image unmixing. The model assumes that the pixel reflectances result from linear combinations of pure component spectra contaminated by an additive Gaussian noise. The abundance parameters a ..."
Abstract

Cited by 52 (28 self)
 Add to MetaCart
(Show Context)
Abstract—This paper proposes a hierarchical Bayesian model that can be used for semisupervised hyperspectral image unmixing. The model assumes that the pixel reflectances result from linear combinations of pure component spectra contaminated by an additive Gaussian noise. The abundance parameters appearing in this model satisfy positivity and additivity constraints. These constraints are naturally expressed in a Bayesian context by using appropriate abundance prior distributions. The posterior distributions of the unknown model parameters are then derived. A Gibbs sampler allows one to draw samples distributed according to the posteriors of interest and to estimate the unknown abundances. An extension of the algorithm is finally studied for mixtures with unknown numbers of spectral components belonging to a know library. The performance of the different unmixing strategies is evaluated via simulations conducted on synthetic and real data. Index Terms—Gibbs sampler, hierarchical Bayesian analysis, hyperspectral images, linear spectral unmixing, Markov chain Monte Carlo (MCMC) methods, reversible jumps. I.
Analysis of polyphonic audio using sourcefilter model and nonnegative matrix factorization
 in Advances in Models for Acoustic Processing, Neural Information Processing Systems Workshop
, 2006
"... •Framework for (polyphonic) audio — linear signal model for magnitude spectrum xt(k): x̂t(k) = N∑ ..."
Abstract

Cited by 22 (3 self)
 Add to MetaCart
(Show Context)
•Framework for (polyphonic) audio — linear signal model for magnitude spectrum xt(k): x̂t(k) = N∑
Joint Detection and Tracking of TimeVarying Harmonic Components: a Flexible Bayesian Approach
 in &quot;IEEE transactions on Speech, Audio and Language Processing
, 2006
"... This paper addresses the joint estimation and detection of timevarying harmonic components in audio signals. We follow a flexible viewpoint, where several frequency/amplitude trajectories are tracked in spectrogram using particle filtering. The core idea is that each harmonic component (composed of ..."
Abstract

Cited by 15 (0 self)
 Add to MetaCart
(Show Context)
This paper addresses the joint estimation and detection of timevarying harmonic components in audio signals. We follow a flexible viewpoint, where several frequency/amplitude trajectories are tracked in spectrogram using particle filtering. The core idea is that each harmonic component (composed of a fundamental partial together with several overtone partials) is considered a target. Tracking requires to define a statespace model with state transition and measurement equations. Particle filtering algorithms rely on a socalled sequential importance distribution, and we show that it can be built on previous multipitch estimation algorithms, so as to yield an even more efficient estimation procedure with established convergence properties. Moreover, as our model captures all the harmonic model information, it actually separates the harmonic sources. Simulations on synthetic and real music data show the interest of our approach.
Unsupervised SingleChannel Music Source Separation by Average Harmonic Structure Modeling
 IEEE Transactions on Audio, Speech and Language Processing
, 2008
"... ..."
(Show Context)
Automatic transcription of piano music based on HMM tracking of jointlyestimated pitches
 in Proc of the 4th Music Information Retrieval Evaluation eXchange (MIREX
, 2008
"... This work deals with the automatic transcription of piano recordings into a MIDI symbolic file. The system consists of subsequent stages of onset detection and multipitch estimation and tracking. The latter is based on a Hidden Markov Model framework, embedding a spectral maximum likelihood method f ..."
Abstract

Cited by 12 (3 self)
 Add to MetaCart
(Show Context)
This work deals with the automatic transcription of piano recordings into a MIDI symbolic file. The system consists of subsequent stages of onset detection and multipitch estimation and tracking. The latter is based on a Hidden Markov Model framework, embedding a spectral maximum likelihood method for joint pitch estimation. The complexity issue of joint estimation techniques is solved by selecting subsets of simultaneously played notes within a preestimated set of candidates. Tests on a large database and comparisons to stateoftheart methods show promising results. 1.
Estimating the number of endmembers in hyperspectral images using the normal compositional model and a hierarchical Bayesian algorithm
 Department of Electrical Engineering and Computer Science, University of Michigan, Ann
, 1984
"... Abstract—This paper studies a semisupervised Bayesian unmixing algorithm for hyperspectral images. This algorithm is based on the normal compositional model recently introduced by Eismann and Stein. The normal compositional model assumes that each pixel of the image is modeled as a linear combinati ..."
Abstract

Cited by 10 (5 self)
 Add to MetaCart
(Show Context)
Abstract—This paper studies a semisupervised Bayesian unmixing algorithm for hyperspectral images. This algorithm is based on the normal compositional model recently introduced by Eismann and Stein. The normal compositional model assumes that each pixel of the image is modeled as a linear combination of an unknown number of pure materials, called endmembers. However, contrary to the classical linear mixing model, these endmembers are supposed to be random in order to model uncertainties regarding their knowledge. This paper proposes to estimate the mixture coefficients of the Normal Compositional Model (referred to as abundances) as well as their number using a reversible jump Bayesian algorithm. The performance of the proposed methodology is evaluated thanks to simulations conducted on synthetic and real AVIRIS images. Index Terms—Bayesian inference, hyperspectral images, Monte Carlo methods, normal compositional model, reversible jump,
MULTIPITCH ESTIMATION OF QUASIHARMONIC SOUNDS IN COLORED NOISE
"... This paper proposes a new multipitch estimator based on a likelihood maximization principle. For each tone, a sinusoidal model is assumed with a colored, MovingAverage, background noise and an autoregressive spectral envelope for the overtones. A monopitch estimator is derived following a Weighted ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
(Show Context)
This paper proposes a new multipitch estimator based on a likelihood maximization principle. For each tone, a sinusoidal model is assumed with a colored, MovingAverage, background noise and an autoregressive spectral envelope for the overtones. A monopitch estimator is derived following a Weighted Maximum Likelihood principle and leads to find the fundamental frequency (F0) which jointly maximally flattens the noise spectrum and the sinusoidal spectrum. The multipitch estimator is obtained by extending the method for jointly estimating multiple F0’s. An application to piano tones is presented, which takes into account the inharmonicity of the overtone series for this instrument. 1.
Multipitch streaming of harmonic sound mixtures
 IEEE Trans. Audio
"... Abstract—Multipitch analysis of concurrent sound sources is an important but challenging problem. It requires estimating pitch values of all harmonic sources in individual frames and streaming the pitch estimates into trajectories, each of which corresponds to a source. We address the streaming pro ..."
Abstract

Cited by 4 (3 self)
 Add to MetaCart
(Show Context)
Abstract—Multipitch analysis of concurrent sound sources is an important but challenging problem. It requires estimating pitch values of all harmonic sources in individual frames and streaming the pitch estimates into trajectories, each of which corresponds to a source. We address the streaming problem for monophonic sound sources. We take the original audio, plus framelevel pitch estimates from any multipitch estimation algorithm as inputs, and output a pitch trajectory for each source. Our approach does not require pretraining of source models from isolated recordings. Instead, it casts the problem as a constrained clustering problem, where each cluster corresponds to a source. The clustering objective is to minimize the timbre inconsistency within each cluster. We explore different timbre features for music and speech. For music, harmonic structure and a newly proposed feature called uniform discrete cepstrum (UDC) are found effective; while for speech, MFCC and UDC works well. We also show that timbreconsistency is insufficient for effective streaming. Constraints are imposed on pairs of pitch estimates according to their timefrequency relationships. We propose a new constrained clustering algorithm that satisfies as many constraints as possible while optimizing the clustering objective. We compare the proposed approach with other stateoftheart supervised and unsupervised multipitch streaming approaches that are specifically designed for music or speech. Better or comparable results are shown. Index Terms—Multipitch analysis, pitch streaming, timbre tracking, cochannel speech, constrained clustering. I.
Default Bayesian estimation of the fundamental frequency
 IEEE Trans. on ASLP
, 2013
"... Abstract—Joint fundamental frequency and model order estimation is an important problem in several applications. In this paper, a default estimation algorithm based on a minimum of prior information is presented. The algorithm is developed in a Bayesian framework, and it can be applied to both real ..."
Abstract

Cited by 4 (3 self)
 Add to MetaCart
(Show Context)
Abstract—Joint fundamental frequency and model order estimation is an important problem in several applications. In this paper, a default estimation algorithm based on a minimum of prior information is presented. The algorithm is developed in a Bayesian framework, and it can be applied to both real and complexvalued discretetime signals which may have missing samples or may have been sampled at a nonuniform sampling frequency. The observation model and prior distributions corresponding to the prior information are derived in a consistent fashion using maximum entropy and invariance arguments. Moreover, several approximations of the posterior distributions on the fundamental frequency and the model order are derived, and one of the stateoftheart joint fundamental frequency and model order estimators is demonstrated to be a special case of one of these approximations. The performance of the approximations are evaluated in a smallscale simulation study on both synthetic and real world signals. The simulations indicate that the proposed algorithm yields more accurate results than previous algorithms. The simulation code is available online. Index Terms—Fundamental frequency estimation, Bayesian model comparison, Zellner’s gprior.
Bayesian Model Comparison with the gPrior
"... Abstract—Model comparison and selection is an important problem in many modelbased signal processing applications. Often, very simple information criteria such as the Akaike information criterion or the Bayesian information criterion are used despite their shortcomings. Compared to these methods, D ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Abstract—Model comparison and selection is an important problem in many modelbased signal processing applications. Often, very simple information criteria such as the Akaike information criterion or the Bayesian information criterion are used despite their shortcomings. Compared to these methods, Djuric’s asymptotic MAP rule was an improvement, and in this paper we extend the work by Djuric in several ways. Specifically, we consider the elicitation of proper prior distributions, treat the case of real and complexvalued data simultaneously in a Bayesian framework similar to that considered by Djuric, and develop new model selection rules for a regression model containing both linear and nonlinear parameters. Moreover, we use this framework to give a new interpretation of the popular information criteria and relate their performance to the signaltonoise ratio of the data. By use of simulations, we also demonstrate that our proposed model comparison and selection rules outperform the traditional information criteria both in terms of detecting the true model and in terms of predicting unobserved data. The simulation code is available online. Index Terms—Bayesian model comparison, Zellner’s gprior, AIC, BIC, Asymptotic MAP. I.