CAJ | 학술논문

为了进一步减少压缩感知中语音信号观测序列的数据传输量,文中采用基因表达式编程( Gene Expression Pro-gramming,GEP)算法对语音信号的观测序列进行建模与预测,同时引入观测序列建模预测后的压缩感知理论框架来解决该问题。首先,分析了压缩感知中语音信号观测序列的相关特性,然后利用GEP算法对语音信号观测序列建立了精确的非线性模型结构,最终实现原始语音信号的重构。实验结果表明,该算法在保证重构语音的性能的前提下,可以进一步减少语音信号观测序列的传输量,最终实现语音信号的二次压缩。
위료진일보감소압축감지중어음신호관측서렬적수거전수량,문중채용기인표체식편정( Gene Expression Pro-gramming,GEP)산법대어음신호적관측서렬진행건모여예측,동시인입관측서렬건모예측후적압축감지이론광가래해결해문제。수선,분석료압축감지중어음신호관측서렬적상관특성,연후이용GEP산법대어음신호관측서렬건립료정학적비선성모형결구,최종실현원시어음신호적중구。실험결과표명,해산법재보증중구어음적성능적전제하,가이진일보감소어음신호관측서렬적전수량,최종실현어음신호적이차압축。
In order to reduce the amount of data transmission of speech signals measurements sequence in compressed sensing,use GEP al-gorithm to model and predict for the measurements sequence of speech signal,and a CS theoretical framework is proposed after predicting and modeling the measurements sequence to fix this question. First,analyze the relevant characteristics of the measurements sequence of speech signal in compressed sensing. Then using GEP algorithm,build an accurate nonlinearity model structure for speech signals meas-urements sequence. Finally,achieve the goal of rebuilding original signals. Showed by experiment,this algorithm can further reduce the a-mount of measurements sequence,while ensuring the performance of reconstructed speech signals,to achieve the purpose of secondary compression of speech signals.