基于语音分段的自适应时长调整算法  

Adaptive Time Scale Modification Algorithm Based on Speech Segment Processing

作　　者：谢贵武 杨继红[1] 肖勇[2] 闵刚[2] 

机构地区：[1]中国人民解放军63880部队 [2]解放军理工大学通信工程学院研究生2队

出　　处：《军事通信技术》2008年第2期56-59,104,共5页Journal of Military Communications Technology

摘　　要：文中提出了一种自适应的语音时长调整算法,首先对语音分段,提取出稳定的语音段使之与音素或者音节基本对应,然后根据总调整因子β和各段语音长度分配每一个语音段的局部调整因子iβ,最后采用波形相似叠加(W SOLA)算法完成对语音的时长调整。仿真结果表明:文中算法实用有效,可以合成可懂度和自然度更高的语音。An adaptive algorithm for time-scaling of speech was proposed in this paper.Firstly,the speech signal was divided into a series of steady segments,each of which corresponds to a phoneme or a syllable respectively.Then,every speech segment was allocated a local modification factor βi according to the total modification factor β and its length.Finally,the entire speech signal was time scaled using WSOLA algorithm.Simulation shows that the new algorithm is efficient and the synthesized speech is more intelligible and natural.

关 键 词：时长调整 语音分段 波形相似叠加 

分 类 号：TN91[电子电信—通信与信息系统]