logo Idiap Research Institute        
 [BibTeX] [Marc21]
Convolutional Pitch Target Approximation Model for Speech Synthesis
Type of publication: Idiap-RR
Citation: Na_Idiap-RR-05-2013
Number: Idiap-RR-05-2013
Year: 2013
Month: 3
Institution: Idiap
Abstract: In this paper, we investigate pitch contour modelling in speech synthesis based on segmental units. A convolutional pitch target approximation model is proposed. This model allows jointly stochastic modelling of framewise pitch and pitch contour of longer units, of which the intuitive relations are revealed by a convolutional target approximation filter. The pitch contour is stylized by a linear representation called pitch target. In synthesis stage, the likelihood of the framewise model and the pitch target model are jointly maximized using a Toeplitz matrix representing the discrete convolutional filter.
Keywords: Pitch modelling, pitch target approximation, speech synthesis
Projects Idiap
Authors Na, Xingyu
Garner, Philip N.
Added by: [ADM]
Total mark: 0
  • Na_Idiap-RR-05-2013.pdf (MD5: 95d7dd877584f46866ae46215783aae6)