基于LPC的语音信号特征参数提取算法研究.docx

文档介绍：第 29 卷第 4 期
2015 年 8 月
商洛学院学报
Journal of Shangluo University
 Aug. 2015
doi:.1674-
基于 LPC 的语音信号特征参数提取算法研究
李亚文
(商洛学院电子信息与电气工程学院,陕西商洛 726000)
摘要:提出了一种基于 LPC 的语音信号特征参数提取的算法思想,对原始的语音信号进行线性预测建模,估计预算模型参数,提取 LPC 系数,分析 LPC 倒谱并计算预测误差。实验结果表明,该算法能较好的提取语音信号的特征参数,且预测重构的语音信号误差较小, 易于建模的实现,为语音信号处理提供了一种特征参数提取的方法。
关键词:LPC;系统函数;预测误差;倒谱系数
中图分类号: 文献标识码:A 文章编号:1674-0033(2015)04-0025-04
A LPC-based New Algorithm Research of Extracting Feature Parameters of Speech Signal
LI Ya-wen
(College of Electronic Information and Electrical Engineering, Shangluo University, Shangluo 726000, Shaanxi)
Abstract: An algorithm idea of linear predictive coding in speech feature coefficients extraction is proposed, with linear prediction modeling with the original speech signal,estimation of budget model parameters, extraction of linear predictive coding coefficient, analysis of linear predictive coding cepstrum and calculating of the predictive error. The experiment result snows that the proposed algorithm is invisible and maneuverable to extract the feature parameters, and precision of the reconstruction speech signal with the less prediction error, a new method of extracting the feature parameters is proposed for speech signal processing.
Key words:linear predictive coding; system function; prediction error; cepstrum coefficient
LPC(linear predictiv