Font Size: a A A

Research On The Timing And Prediction Function In DIVA Model

Posted on:2015-07-05Degree:MasterType:Thesis
Country:ChinaCandidate:C Y ZhouFull Text:PDF
GTID:2284330467477064Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
In recent years, it is the key idea of designing the speech synthesis system to describe andsimulate the functions corresponding to the associated brain areas and cerebellum areas, which areinvolved in speech production and acquisition at the level of neuroanatomy and neuropsycology.Around this topic, great efforts were made in researching and discussing the computational modelof speech production and acquitision. The most outstanding model is the DIVA (Directions IntoVelocities of Articulators) model which is proposed by the professor Frank Guenther and hiscolleges in speech lab, Boston University. The DIVA model is a neural network model describingthe process of speech production and acquisition to product word, syllable, and phonemes bycontrolling a simulated vocal tract.First, the developing process of the DIVA model is introduced. The associated theory of DIVAmodel is illustrated in detail, which include the basic concept and construction of the DIVA model,and the learning phase and imitation phase.Second, the region of interest, ROI is introduced, and the speech related ROI in brain, other ROIin brain and the cerebellum ROI was in detail respectively.Third, in order to solve the cerebellum timing function in DIVA model, after analyzing thefeedforward control subsystem, the RSL model is introduced. Then the DIVA model is modified byusing RSL cerebellum system, so as to adjust the cerebellum delay in the subsystem. The simulationresults demonstrates that the modification makes the cerebellum timing function more accurate, andalso reduces the error in speech production.At last, on the basis of introducing the hireachical state feedback control model, the DIVAmodel is compared to the HSFC model. And the HSFC model is applied to the DIVA model. Theexperiment result shows that the modification can effectively improve the accuaracy of predictionfurther to decrease the error in speech production.This article aims to improve the precision and accuracy of the DIVA model, which has positiveeffect on promoting the development of neuropsychology and neuroanatomy,and the research anddevelopment of medical equipments.
Keywords/Search Tags:DIVA model, cerebellum, timing, hireachical state feedback control model, region ofinterest
PDF Full Text Request
Related items