Now showing items 1-6 of 6

    • Autoregressive clustering for HMM speech synthesis 

      Shannon, Matt; Byrne, William (ISCA (International Speech Communication Association), 2010-09-27)
      The autoregressive HMM has been shown to provide efficient parameter estimation and high-quality synthesis, but in previous experiments decision trees derived from a non-autoregressive system were used. In this paper ...
    • Autoregressive HMMs for speech synthesis 

      Shannon, Matt; Byrne, William (ISCA (International Speech Communication Association), 2009-09-07)
      We propose the autoregressive HMM for speech synthesis. We show that the autoregressive HMM supports efficient EM parameter estimation and that we can use established effective synthesis techniques such as synthesis ...
    • Autoregressive models for statistical parametric speech synthesis 

      Shannon, Matt; Zen, Heiga; Byrne, William (IEEE (Institute of Electrical and Electronics Engineers), 2013-03)
      We propose using the autoregressive hidden Markov model (HMM) for speech synthesis. The autoregressive HMM uses the same model for parameter estimation and synthesis in a consistent way, in contrast to the standard approach ...
    • The effect of using normalized models in statistical speech synthesis 

      Shannon, Matt; Zen, Heiga; Byrne, William (ISCA (International Speech Communication Association), 2011-08-27)
      The standard approach to HMM-based speech synthesis is inconsistent in the enforcement of the deterministic constraints between static and dynamic features. The trajectory HMM and autoregressive HMM have been proposed as ...
    • Fast, low-artifact speech synthesis considering global variance 

      Shannon, Matt; Byrne, William (IEEE (Institute of Electrical and Electronics Engineers), 2013-05-27)
      Speech parameter generation considering global variance (GV generation) is widely acknowledged to dramatically improve the quality of synthetic speech generated by HMM-based systems. However it is slower and has higher ...
    • A formulation of the autoregressive HMM for speech synthesis 

      Shannon, Matt; Byrne, William (Department of Engineering, University of Cambridge, 2009-08-31)
      We present a formulation of the autoregressive HMM for speech synthesis and compare it to the standard HMM synthesis framework and the trajectory HMM. We give details of how to do efficient parameter estimation and synthesis ...