Sabiia Seb
        Busca avançada

Botão Atualizar

Botão Atualizar

Registro completo
Provedor de dados:  InTech
País:  N/A
Título:  Imitation Learning Based Talking Heads in Humanoid Robotics
Autores:  Enzo Mumolo
Massimiliano Nolich
Data:  2007-06-01
Ano:  2007
Palavras-chave:  Humanoid Robots
Human-like Machines
Resumo:  The estimation of articulatory static and dynamic configuration is one of the most difficult problems in voice technology. Several approaches have been attemped during the past years, and most of the difficulties are due to the fact that the articulatory-acoustic relation is not unique: different articulatory configurations can produce the same signal. The problem can be faced with suitable constraints which are needed to avoid the unrealistic configurations. One on the last work in this area has been reported in [60], which estimated articulatory parameters by finding the maximum a posteriori estimate of articulatory parameters for a given speech spectrum and the state sequence of a HMM--based speech production model. This model consists of HMMs of articulatory parameters for each phoneme and an articulatory-to-acoustic mapping that transforms the articulatory parameters into the speech spectrum for each HMM state. The authors constructed the model by using simultaneously observed articulatory and acoustic data for sentence utterances, which was collected by using an electro-magnetic articulo-graphic (EMA) system. Our system does not use EMA at all, trying to get the right articulations with several penalty factors. For this reason, the audio-video result is not always correct and it needs a judgment by the operator. We emphasize the following final remarks.
Tipo:  25
Idioma:  Inglês
Editor:  INTECH Open Access Publisher
Relação:  ISBN:978-3-902613-07-3

Empresa Brasileira de Pesquisa Agropecuária - Embrapa
Todos os direitos reservados, conforme Lei n° 9.610
Política de Privacidade
Área restrita

Parque Estação Biológica - PqEB s/n°
Brasília, DF - Brasil - CEP 70770-901
Fone: (61) 3448-4433 - Fax: (61) 3448-4890 / 3448-4891 SAC:

Valid HTML 4.01 Transitional