Title :
Mandarin singing voice synthesis using ANN vibrato parameter models
Author :
Gu, Hung-Yan ; Lin, Zheng-fu
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ. of Sci. & Technol., Taipei
Abstract :
In this paper, the vibrato parameters of sung syllables are analyzed by using short-time Fourier transform and the method of analytic signal. After the vibrato parameter values for all training syllables are obtained, they are used to train an artificial neural network (ANN) for each type of vibrato parameter. Then, these ANN models are used to generate the values of vibrato parameters. Next, these parameter values and other music information are used together to control a harmonic-plus-noise (HNM) model to synthesize singing voice signals. With the synthetic singing voice, subjective perception tests are conducted. The result show that the singing voice synthesized with the ANN generated vibrato parameters is apparently more natural than the singing voice synthesized with fixed vibrato parameters.
Keywords :
Fourier transforms; neural nets; speech synthesis; ANN generated vibrato parameters; ANN vibrato parameter models; Mandarin singing voice synthesis; analytic signal; artificial neural network; fixed vibrato parameters; harmonic-plus-noise model; short-time Fourier transform; subjective perception tests; sung syllables; synthetic singing voice; training syllables; vibrato parameter values; Artificial neural networks; Computer science; Cybernetics; Frequency estimation; Information analysis; Machine learning; Network synthesis; Signal analysis; Signal synthesis; Speech analysis; Singing voice; artificial neural network; harmonic-plus-noise model; signal synthesis; vibrato parameter;
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
DOI :
10.1109/ICMLC.2008.4620973
