Skip to Main content Skip to Navigation
Conference papers

Prior and posterior probabilistic models of uncertainties in a model for producing voice

Abstract : The aim of this paper is to use Bayesian statistics to update a probability density function related to the tension parameter, which is one of the main parameters responsible for the changing of the fundamental frequency of a voice signal, generated by a mechanical/mathematical model for producing voiced sounds. We follow a parametric approach for stochastic modeling, which requires the adoption of random variables to represent the uncertain parameters present in the cited model. For each random variable, a probability density function is constructed using the Maximum Entropy Principle and the Monte Carlo method is used to generate voice signals as the output of the model. Then, a probability density function of the voice fundamental frequency is constructed. The random variables are fit to experimental data so that the probability density function of the fundamental frequency obtained by the model can be as near as possible of a probability density function obtained from experimental data. New values are obtained experimentally for the fundamental frequency and they are used to update the probability density function of the tension parameter, via Bayes's Theorem.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal-upec-upem.archives-ouvertes.fr/hal-00684326
Contributor : Christian Soize <>
Submitted on : Sunday, April 1, 2012 - 3:46:30 PM
Last modification on : Thursday, March 19, 2020 - 11:52:03 AM
Long-term archiving on: : Wednesday, December 14, 2016 - 7:28:54 PM

File

conference-2010-WCCM-2010-cata...
Files produced by the author(s)

Identifiers

Collections

Citation

E. Cataldo, R. Sampaio, Christian Soize. Prior and posterior probabilistic models of uncertainties in a model for producing voice. 9th World Congress on Computational Mechanics/4th Asian Pacific Congress on Computational Mechanics, Jul 2010, Sydney, Australia. pp.Article Number: 012195, ⟨10.1088/1757-899X/10/1/012195⟩. ⟨hal-00684326⟩

Share

Metrics