MELP语音编解码算法在DSP上的优化  

Optimization for Algorithm of MELP Speech Codec Based on DSP Platform

作　　者：李洋[1] 吴玉成[1] 

机构地区：[1]重庆大学通信工程学院,重庆400044

出　　处：《电声技术》2010年第5期44-47,共4页Audio Engineering

摘　　要：为了满足实际工程的需要,混合激励线性预测(MELP)语音编解码算法在DSP平台实现需要进行优化。以工程测试数据为佐证,运用编译器优化、inline函数优化、内联函数优化等不同方法对MELP语音编解码算法DSP程序进行优化。分析和对比了各种优化方法的优缺点和测试结果,表明优化结果达到了实际工程的需要,经过测试效果良好,具有实际意义。In order to meet the need of engineering application, the algorithm of the MELP（Mixed-Excitation Linear Prediction） speech codec on the DSP platform needs to be optimized. Based on the data, the code of the MELP speech codec is optimized by using different methods which includes compiler tools, small function inline expansion and intrinsics and so on. Furthermore, by analyzing and comparing the performance of various optimization methods and results, it shows that the tested results meet the practical application with good effects and practical significance.

关 键 词：混合激励线性预测 DSP 实时性 优化 

分 类 号：TN912[电子电信—通信与信息系统]