| This dissertation addresses the problem of speech synthesis and speech production modelling based on the fundamental principles of human speech production. Unlike the conventional source-filter model, which assumes the independence of the excitation and the acoustic filter, we treat the entire vocal apparatus as one system consisting of a fluid dynamic aspect and a mechanical part. We model the vocal tract by a three-dimensional moving geometry. We also model the sound propagation inside the vocal apparatus as a three-dimensional nonplane-wave propagation inside a viscous fluid described by Navier-Stokes equations.; In our work, we first propose a combined minimum energy and minimum jerk criterion to estimate the dynamic vocal tract movements during speech production. Both theoretical error bound analysis and experimental results show that this method can achieve very close match at the target points and avoid the abrupt change in articulatory trajectory at the same time. Second, a mechanical vocal fold model is used to compute the excitation signal of the vocal tract. The advantage of this model is that it is closely coupled with the vocal tract system based on fundamental aerodynamics. As a result, we can obtain an excitation signal with much more detail than the conventional parametric vocal fold excitation model. Furthermore, strong evidence of source-tract interaction is observed.; Finally, we propose a computational model of the fricative and stop types of sounds based on the physical principles of speech production. The advantage of this model is that it uses an exogenous process to model the additional nonsteady and nonlinear effects due to the flow mode, which are ignored by the conventional source-filter speech production model. A recursive algorithm is used to estimate the model parameters. Experimental results show that this model is able to synthesize good quality fricative and stop types of sounds.; Based on our dissertation work, we carefully argue that the articulatory speech production model has the potential to flexibly synthesize natural-quality speech sounds and to provide a compact computational model for speech production that can be beneficial to a wide range of areas in speech signal processing. |
