[1]李燕萍 张玲华.基于多时间尺度韵律特征分析的语音转换研究[J].计算机技术与发展,2012,(12):67-70.
　LI Yan-ping,ZHANG Ling-hua.Voice Conversion Research Based on Multi-time Scale Prosodic Feature Analysis[J].,2012,(12):67-70.
点击复制

基于多时间尺度韵律特征分析的语音转换研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2012年12期
页码:
67-70
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Voice Conversion Research Based on Multi-time Scale Prosodic Feature Analysis
文章编号:
1673-629X（2012）12-0067-04
作者:
李燕萍 张玲华
南京邮电大学通信与信息工程学院
Author(s):
LI Yan-ping; ZHANG Ling-hua
College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications
关键词:
语音转换; 韵律; 多时问尺度; 高斯混合模型
Keywords:
voice conversion;  prosody ;  multi-time scale;  Gaussian mixture model
分类号:
TP31
文献标志码:
A
摘要:
为了提高转换语音的可懂度与自然度，文中在语音信号的特征抽取方面，注重对语音信号韵律特性的研究，提出了一种多时间尺度的韵律特性抽取方法及其参数化表示，基于逐级细化的策略实现语音信号在多时间尺度下的韵律特征分析与提取，实现对韵律特性从整体到局部细致完整地刻画，克服了韵律信息表述的模糊性和复杂性。实验结果表明，文中提出的语音转换系统在四种测试类型中性能良好，与现有的高斯混合模型相比，ABX测试结果提高了10．88％，同时MOS得分平均提高了18．59％
Abstract:
In order to improve the conversion speech intelligibility and natural degrees, based on speech signal feature extraction, pay great attention to the research of speech signal prosody characteristics, put forward a prosody characteristics extraction method based on multi-time scale and parameterized representation. Based on stepwise refinement strategy, achieve the implementation of prosodic feature extraction on different time scales, which can enable detailed full description for prosodic information from global to local,overcome the ambi guity and complexity of prosody characterization. The experimental results show that the performance of proposed voice conversion sys tem in four test type is good,and compared with existing Gaussian mixture model,ABX test results increased by 10.88% ,and at the same time,MOS scoring average is improved by 18.59%

相似文献/References:

[1]翟继友 张鹏.高斯混合模型参数估值算法的优化[J].计算机技术与发展,2011,(11):145.
　ZHAI Ji-you,ZHANG Peng.Optimization of Parameter Estimation Based on Gaussian Mixture Model[J].,2011,(12):145.
[2]董添辉[],张玲华[]. 粒子群优化径向基函数网络的语音转换[J].计算机技术与发展,2017,27(05):64.
　DONG Tian-hui[],ZHANG Ling-hua[]. Voice Conversion of Radial Basic Function Neural Network of ParticleSwarm Optimization[J].,2017,27(12):64.

备注/Memo

备注/Memo:
国家自然科学基金资助项目（60902065,61001152,61172118）;浙江省自然科学基金（Y1090649）;南京邮电大学引进人才基金（NY209004）李燕萍（1983-），女，陕西渭南人，博士，讲师，研究方向为语音转换、说话人识别；张玲华，教授，博士生导师，研究方向为语音增强、多媒体通信
更新日期/Last Update: 1900-01-01