Publicação

Phoneme dedicated ANN improves segmental duration model

Ver documento

Detalhes bibliográficos
Resumo:The Phoneme Dedicated Artificial Neural Network (PDANN) segmental duration model consists of a set of ANNs trained specifically for each phoneme segment in order to avoid miscellaneous influence of (]iffen nt. yp( S of phouem(·! segments. Therefow, each ANN is dedicated to predict the duration of a specific phoneme segment. Objective and subjective measurements of t he performance of the PDANN model were compared with those of a typical ANN model using the same input features and database.
Autores principais:Teixeira, João Paulo
Outros Autores:Freitas, Diamantino Silva
Ano:2008
País:Portugal
Tipo de documento:documento de conferência
Tipo de acesso:acesso aberto
Instituição associada:Instituto Politécnico de Bragança
Idioma:inglês
Origem:Biblioteca Digital do IPB
Descrição
Resumo:The Phoneme Dedicated Artificial Neural Network (PDANN) segmental duration model consists of a set of ANNs trained specifically for each phoneme segment in order to avoid miscellaneous influence of (]iffen nt. yp( S of phouem(·! segments. Therefow, each ANN is dedicated to predict the duration of a specific phoneme segment. Objective and subjective measurements of t he performance of the PDANN model were compared with those of a typical ANN model using the same input features and database.