首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于WSOLA算法的语音时长调整研究
引用本文:叶锡恩,张巧文.基于WSOLA算法的语音时长调整研究[J].科技通报,2005,21(5):593-596,611.
作者姓名:叶锡恩  张巧文
作者单位:宁波大学,电路与系统研究所,宁波,315211;南京大学,近代声学国家重点实验室,南京,210093;宁波大学,电路与系统研究所,宁波,315211;南京大学,近代声学国家重点实验室,南京,210093
基金项目:浙江省科技厅项目(2003C31078);南京大学近代声学国家重点实验室资助项目(0107);宁波市科技攻关项目(20038100l1)
摘    要:目前的PSOLA算法进行时长调整时,其计算量大,很难实现实时变速不变调处理。利用波形相似性来解决语音时长调整的WSOLA算法,实验证明能生成高品质的语音;在算法上高效、鲁棒.可以通过修改调整因子α实现连续范同内的在线语音时长调整。此算法已应用在数字语音教学系统中.具有良好的实时性和高品质语音。

关 键 词:信号与信息处理  短时傅立叶变换  时长调整  互相关系数  调整因子α
文章编号:1001-7119(2005)05-0593-04
收稿时间:2004-05-26
修稿时间:2004-05-26

Study on Time-Scale Modification of Speech Based on WSOLA
YE Xi-en,ZHANG Qiao-wen.Study on Time-Scale Modification of Speech Based on WSOLA[J].Bulletin of Science and Technology,2005,21(5):593-596,611.
Authors:YE Xi-en  ZHANG Qiao-wen
Abstract:PSOLA, a popular algorithm for time-scale modification, has heavy computation, which is very difficult for onling operation. Waveform similarity is proposed for tackling the problem of time-scale modification of speech, which is called WSOLA algorithm, through experiments produces the high quality speech output, is algorithmically and computationally efficient and robust, and allows for on-ling processing with arbitrary time-scaling actors chosen over a wide con- tinuous range of values. The algorithm has already been used in the tutoring system of the digital speech, having good real-time quality and high quality speech.
Keywords:
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号