语音时长规整技术的研究回溯  

A Survey of Time Scale Modification of Speech

作　　者：周俊[1] 高悦[1] 谭薇[1] 陈砚圃[1] 

机构地区：[1]西安通信学院,陕西西安710106

出　　处：《现代电子技术》2006年第18期102-105,共4页Modern Electronics Technique

摘　　要：语音时长规整技术是在不改变语音音调并保证良好音质的情况下,对语音进行一定的压缩或拉伸的技术。首先给出了语音时长规整技术的发展历程和主要实现方法,重点阐述了主要实现算法的原理,并仿真实现了适合实时处理的两种时域算法,比较分析了两种时域方法的效果。最后对语音时长规整技术进行了展望。Time scale modification of speech refers to processing performed on speech signals that changes the perceived rate of articulation without affecting the pitch or intelligibility of the speech. This paper describes the history of TSM of speech and the main methods. The two time domain algorithms are discussed and simulated in detail,some results are analyzed simul- taneously. A technological outlook for this speech technique is given in the last session.

关 键 词：时长规整 固定同步叠加 相位声码器 正弦模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]