一种改进的语音信号特征参数提取算法研究  

An improved speech signal feature extraction algorithm research

作　　者：王彪[1] 

机构地区：[1]宝鸡文理学院数学系,陕西宝鸡721013

出　　处：《电子设计工程》2011年第21期59-61,共3页Electronic Design Engineering

摘　　要：为了提高语音信号的识别率,提出了一种改进的语音信号特征提取算法。该算法在MFCC参数的基础上,增加每帧信号的短时能量和短时过零率,使得新参数能够更为准确地表征语音信号。通过仿真实验,说明了新特征参数取得了较高的识别率。In order to improve the speech recognition rate, an improved speech signal feature extraction algorithm is presented. The short-time energy and short-time zero-crossing rate of each frame signal based on MFCC parameters are increased in the algorithm ,which make the new parameters can provide a more accurate representation of speech signals. It is explained that the new feature parameters obtains high recognition rate through the simulation experiments.

关 键 词：特征提取 短时能量 短时过零率 MFCC 语音信号 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]