基于信道软输出及信源参数相关性的联合语音解码  

Joint Speech Decoding Based on Channel Soft-Value and Bayes Estimation

作　　者：周琳[1] 吴镇扬[1] 

机构地区：[1]东南大学无线电工程系,江苏南京210096

出　　处：《应用科学学报》2005年第3期240-244,共5页Journal of Applied Sciences

摘　　要：提出一种基于接收端的联合语音解码算法,根据信道或信道解码提供的参数软输出值,以及语音编码参数的冗余量计算接收参数的后验概率;利用后验概率基于MAP或MS准则进行参数估计,最佳估计值进行语音解码.仿真中采用G.711和GSMEFR两种语音编码标准,结果表明联合解码算法显著提高了解码语音信噪比.A joint speech-decoding algorithm is proposed in this paper. Based on the soft-value of channel decoder and the redundancy of source parameter, a posterior probability is calculated and used to estimate speech parameter according to MAP/MS criteria. Next the optimal parameter from the estimation model is decoded. Simulation carried our in accordance with G.711 and GSM EFR speech coding standard shows that the joint decoding algorithm obviously improves the SNR of decoded speech.

关 键 词：语音解码 软输出 相关性 源参数 语音编码标准 解码算法 后验概率 最佳估计值 信道解码 接收参数 余量计算 编码参数 参数估计 接收端 MAP GSM EFR 信噪比 

分 类 号：TN912.3[电子电信—通信与信息系统] TN929.5[电子电信—信息与通信工程]