A Speech Recognition System of Adaptive Variation Bird Flock with Fusion Data Normalization

Abstract

The invention relates to the speech recognition technology field, and discloses an adaptive mutation bird swarm speech recognition system integrated with data normalization. A bird swarm individual updating method is optimized by adopting an adaptive mutation method. In the iterative updating initial stage of the bird swarm algorithm, mutation operation is introduced to optimize a parameter adaptive process, and by combining with the data normalization method, a data structure and algorithm complexity are simplified, the swarm diversity of the algorithm is effectively improved, a generalization capability of a model is enhanced, the problems of the algorithm of premature convergence and gradual decreasing of a searching capability along with increasing of generation numbers are solved, and a defect of inclination to local optimization is improved. The adaptive mutation bird swarm speech recognition system has advantages of higher recognition accuracy, faster convergence speed, stronger robustness, and better optimization searching effect.

Description

technical field [0001] The invention relates to the technical field of speech recognition. Background technique [0002] With the development of the information age, human-computer interaction has brought great changes to modern society. Speech recognition, as the basis of human-computer interaction technology, has become a research hotspot in the field of information today. Support vector machine has become a more commonly used classification model in speech recognition technology through its excellent classification ability and good generalization performance. [0003] Support Vector Machine (SVM) is a new machine learning technique based on the principle of structural risk minimization. It can better solve small sample, nonlinear, high-dimensional and other classification problems, and has good generalization, and is widely used in pattern recognition, classification estimation and other problems. The fitting performance and generalization ability of SVM depend on the s...

AI Technical Summary

Problems solved by technology

The grid search (Grid Search, GS) algorithm is a practical parameter optimization method, which divides the parameters to be searched into grids in a given range, and finds the optimal parameters by traversing all the parameter combinations in the grid. The parameter group has the advantage of fast optimization speed, but the grid optimization is highly dependent on the parameter optimization range and optimization step distance

Genetic Algorithm (GA) is an effective optimization method based on the principles of natural selection and genetics proposed by J.H.Holland in the 1970s. It simulates the process of biological evolution and is a global optimization search algorithm with simple and general , the advantage of strong robustness, but the search efficiency is low and premature

Particle Swarm Optimization (PSO) was proposed by Kennedy and Eberhart in 1995. It originated from the study of the predation behavior of birds. It finds the optimal solution through the cooperation among individuals. It has the advantages of simple algorithm and easy implementation. PSO algorithm is easy to fall into local optimum for functions with multiple local extreme points

Images