Convolutional Pitch Target Approximation Model for Speech Synthesis

Other literature type English OPEN
Na, Xingyu ; Garner, Philip N. (2013)
  • Publisher: Idiap
  • Subject: speech synthesis | pitch target approximation | Pitch modelling
    arxiv: Computer Science::Sound

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.
Share - Bookmark