Nonlinear speech coding model based on genetic programming

An improved genetic programming is proposed in this paper to construct the nonlinear models of speech signals, and the speech coding is further accomplished. After the preprocessing of the speech signals, the improved GP is used to construct the corresponding model of each speech frame. Then by analyzing these models, a normalized model that has generalization ability is obtained. And finally the process of speech coding is accomplished by the optimizing the parameters of the normalized model using an optimization algorithm. Experiments demonstrate that the feasibility of the improved GP in the modeling of speech signals, and show the superiority of the proposed method in speech coding based on the comparisons with the linear predictive coding.

Figure optionsDownload as PowerPoint slideHighlights
► An improved genetic programming is proposed for speech modeling.
► We obtain a normalized nonlinear model which is effective for speech coding.
► A new process of speech coding is completed using an improved PSO (UPSO) algorithm.
► We provide a novel method for nonlinear speech processing.