Now showing items 5-6 of 6

    • 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 ...