Descripción
|
|
---|---|
It is known that the amount of characteristics may be the bottleneck of a digital processing system. Finding a good method to detect which characteristics are the most important to identify a speaker would get better results with less characteristics. The classification of an adult speaker by their age is a big challenge since the adulthood is a long period without significant changes in voice. This study proposes a new method based on F-ratio, dispersion metric and also correlation between parameters to find a rank of features. A bootstrapping procedure determines the optimum number of characteristics within a feature vector to characterize a speaker. The results are compared with other non linear ranking methods. The proposed algorithm achieves a better performance in most cases. | |
Internacional
|
Si |
Nombre congreso
|
Recent Advances in Nonlinear Speech Processing |
Tipo de participación
|
960 |
Lugar del congreso
|
Vietri, Italia |
Revisores
|
Si |
ISBN o ISSN
|
2190-3018 |
DOI
|
10.1007/978-3-319-28109-4_29 |
Fecha inicio congreso
|
18/05/2015 |
Fecha fin congreso
|
20/05/2015 |
Desde la página
|
285 |
Hasta la página
|
292 |
Título de las actas
|
Recent Advances in Nonlinear Speech Processing, Smart Innovation, Systems and Technologies |