formularioHidden
formularioRDF
Login

Inscrivez-vous

Ou si vous préférez...

 

Panel Information

Utilizamos cookies propias y de terceros para mejorar tu experiencia de navegación. Al continuar con la navegación entendemos que aceptas nuestra política de cookies.

In

IWANN (), 2011 (), p. 265-272 , -.
Torremolinos
,
Spain
, 2011

Abstract

Oesophageal voice is characterized by its extremely low intelligibility. An algorithm based on Kalman Expectation Maximization (EM) has been developed. The noise presented in the model, state and measurement noise has been optimized in order to improve the algorithm results. The database consists of “a” phonemes of several patients having undergone a total laryngectomy. Additionally, the effect of the algorithm on the UMTS mobile communication context has been tested. The tests show that the algorithm gives the best results when it is used as state noise an oesophageal noise and brown noise as measurement noise. The global percentage enhancement is 75.78%.

À propos de cette ressource...

Visites 67

Catégories: