A hybrid model for speech synthesis

A hybrid model for speech analysis/synthesis is proposed. It relies on a time-varying autoregressive moving-average (ARMA) model and the short-time Fourier transform (STFT). The model is hybrid in that the periodic (narrowband) component in speech is represented in the frequency domain by a harmonic-based STFT, while the random component in speech is represented by a random noise sequence, appropriately shaped by the ARMA model. The time-varying ARMA model has a dual function (namely, it creates a spectral envelope that fits accurately the harmonic STFT components) and provides for the spectral shaping of random noise. This hybrid model essentially incorporates the benefits of waveform coders by employing the STFT and the benefits of traditional vocoders by using an appropriately shaped noise sequence; thus, it is expected to yield robust speech synthesis at low data rates.<>