Unsupervised Signal Restoration in Partially Observed Markov Chains - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Unsupervised Signal Restoration in Partially Observed Markov Chains

Résumé

An important problem in signal processing consists in estimating an unobservable process x = {x n } n∈IN from an observed process y = {y n } n∈IN. In Linear Gaussian Hidden Markov Chains (LGHMC), recursive solutions are given by Kalman-like Bayesian restoration algorithms. In this paper, we consider the more general framework of Linear Gaussian Triplet Markov Chains (LGTMC), i.e. of models in which the triplet (x, r, y) (where r = {r n } n∈IN is some additional process) is Markovian and Gaussian. We address unsupervised restoration in LGTMC by extending to LGTMC the EM parameter estimation algorithm which was already developed in classical state-space models.
Fichier principal
Vignette du fichier
icassp2006.pdf (70.6 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04415440 , version 1 (24-01-2024)

Identifiants

Citer

B.A. El Fquih, François Desbouvries. Unsupervised Signal Restoration in Partially Observed Markov Chains. 2006 IEEE International Conference on Acoustics Speed and Signal Processing, IEEE, May 2006, Toulouse, France. pp.III-13-III-16, ⟨10.1109/ICASSP.2006.1660578⟩. ⟨hal-04415440⟩
0 Consultations
3 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More