Abstract: A computer-implemented method generates a frequency component vector of time series data, by executing a first process and a second process in each unit step. The first process includes: receiving first data; and processing the first data using a first neural network to generate intermediate data. The second process includes: receiving the generated intermediate data; and generating a plurality of component values corresponding to a plurality of frequency bands based on the generated intermediate data such that: a first component value corresponding to a first frequency band is generated using a second neural network based on the generated intermediate data; and a second component value corresponding to a second frequency band different from the first frequency band is generated using the second neural network based on the generated intermediate data and the generated first component value corresponding to the first frequency band.

Abstract: This invention discloses a speech analysis/synthesis method and a simplified form of such a method. Based on a harmonic model, the present method decomposes the parameters of the harmonic model into glottal source characteristics and vocal tract characteristics in its analysis stage and recombines the glottal source and vocal tract characteristics into harmonic model parameters in its synthesis stage.

Abstract: This invention discloses a speech analysis/synthesis method and a simplified form of such a method. Based on a harmonic model, the present method decomposes the parameters of the harmonic model into glottal source characteristics and vocal tract characteristics in its analysis stage and recombines the glottal source and vocal tract characteristics into harmonic model parameters in its synthesis stage.