欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对基本遗传算法（SGA）易于早熟收敛、全局优化速度缓慢、局部搜索能力弱等缺点，提出一种改进型遗传算法（IGA），并将其应用于ACELP语音编码器的代数码书搜索中。改进型算法使用了经验式随机方法初始化种群，设计了与进化代数相关的自适应交叉和变异概率，采取了移民策略维持群体多样性，最后引入了局部爬山搜索机制。将IGA应用于ITU—TG．729A语音编码器，仿真结果表明了该算法的可行性和有效性，从而为代数码书搜索方法的研究提供了新思路。
英文摘要：
Concerning the problems of simple genetic algorithm （SGA）, such as premature convergence, low speed of global optimization and weakness in local search, an improved proposed and applied to algebraic codebook search of ACELP speech coders gen In th etic algorithm （IGA） is e IGA, an empirically - based stochastic method is employed to initialize the population, the crossover and mutation probability de- signed to dynamically adjust to the evolution, the immigration strategy adopted to keep the population di- versity, and the local search mechanism of hill- climbing introduced finally. The proposed method is applied to ITU- T G. 729A, and simulation results indicate its feasibility and effectiveness, thus providing new thinking on algebraic codebook search.
同期刊论文项目
同项目期刊论文
位置：