基于Bloom field模型的基音检测方法  

New Approach of Pitch Detection Based on Bloomfield Model

作　　者：赵小阳[1] 李顺华[1] 岳振军[2] 冯晓雯[3] 

机构地区：[1]解放军理工大学通信工程学院研究生1队,江苏南京210007 [2]解放军理工大学理学院基础电子学系,江苏南京211101 [3]总参谋部通信部驻714厂军代室,江苏南京210002

出　　处：《军事通信技术》2006年第4期10-13,共4页Journal of Military Communications Technology

摘　　要：文中提出了一种改进的基音检测方法,该方法是将B loom fie ld模型引入语音处理领域进行基音检测的一次尝试。仿真结果显示,该方法与传统的自相关法相比,提高了清、浊音判决率,特别是在清、浊音过渡音段,从而改善了语音的基音轨迹。A new approach of pitch detection was proposed in this paper, and it was an attempt to introduce the Bloomfield model into the speech processing. The results of simulation show that the new method has better performance than that of conventional autocorrelation algorithm, especially in the transitional parts between the surd and the sonant. It may get more accurate voiced/unvoiced decisions ,and improve the pitch locus.

关 键 词：布鲁菲尔德模型 基音检测 清 浊音判决 

分 类 号：TN912.3[电子电信—通信与信息系统]