摘要
众所周知,每个人的声调基频是不同的,甚至同一个人在不同情绪下,其声调基频也存在较大的差别。这种差别对于非特定人识别系统的识别率带来了很大的影响,为了减少这种影响,必须采用归一化算法对基频进行处理。文章在几种常用的归一化算法的基础上,提出了一种改进的归一化算法,并对该算法与几种常用算法在相同实验条件下的识别率进行了比较。实验结果表明,该算法有效地提高了声调识别系统的识别率,具有一定的实用价值。
As is known to all,the tone fundamental frequency of everyone is different,even for the same person,its tone fundamental frequency also has bigger difference in different mood. These difference have an effect upon recognition rate of the identification of non specific system,the normalization algorithm must be used to deal with the fundamental frequency in order to reduce these impact. The article propose a modified normalization algorithm on the basis of some commonly used normalization algorithms,and the recognition rates of this algorithm and some commonly used algorithms are compared in the same experimental conditions. The experimental results show that the algorithm is effective to improve the recognition rate of the tone recognition system,and it has certain practical value.
出处
《自动化与仪器仪表》
2016年第1期148-151,共4页
Automation & Instrumentation
关键词
归一化算法
改进LD算法
基频
声调识别
Normalization algorithm
Modified LD algorithm
The fundamental frequency
Tone recognition
