Directly modeling voiced and unvoiced components in speech waveforms by neural networks
ICASSP, pp. 5640-5644, 2016.
This paper proposes a novel acoustic model based on neural networks for statistical parametric speech synthesis. The neural network outputs parameters of a non-zero mean Gaussian process, which defines a probability density function of a speech waveform given linguistic features. The mean and covariance functions of the Gaussian process r...More
Full Text (Upload PDF)
PPT (Upload PPT)