Abstract | ||
---|---|---|
This paper addresses the issue of vowel sound synthesis using a nonlinear model, comprising of a free-running radial basis function (RBF) neural network with global feedback. Voiced speech production is modelled as the output of a nonlinear dynamical system, rather than the conventional linear source-filter approach, which, given the nonlinear nature of speech, is expected to produce more natural-sounding synthetic speech. It is shown that the use of regularisation theory when learning the weights allows stable resynthesis when the network is operated with a global feedback and no external input, correctly producing the desired vowel sound. Additionally it is found that the dynamics of the vowel sound are well modelled, including the inter-pitch variations (jitter), thus making the synthesised vowel more natural-sounding than is possible with simple linear techniques. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1016/S0165-1684(01)00087-1 | Signal Processing |
Keywords | Field | DocType |
Vowel-sound synthesis,Nonlinear dynamics,Radial basis functions,Jitter | Speech synthesis,Radial basis function,Nonlinear system,Speech recognition,Vowel,Jitter,Artificial neural network,Speech production,Mathematics,Gigue | Journal |
Volume | Issue | ISSN |
81 | 8 | 0165-1684 |
Citations | PageRank | References |
5 | 0.53 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Iain Mann | 1 | 10 | 1.42 |
Stephen McLaughlin | 2 | 168 | 16.62 |