期刊文献+

基频轨迹转换算法及在语音转换系统中的应用研究 被引量:1

Morphing Arithmetic of Pitch and Application in Voice Morphing System
在线阅读 下载PDF
导出
摘要 提出并实现了一种基于广义人工神经网络和STRAIGHT模型的高效基频轨迹跟踪算法。一方面,STRAIGHT模型可以对语音信号的基频进行较大幅度的修改而不至于引起合成语音质量的下降。另一方面,利用人工神经网络优良的预测能力,学习源说话人和目标说话人的基频轨迹之间的内在联系,实现基音频率的转换。语谱图分析、主观意见分评价结果表明:提出的基频轨迹跟踪算法在合成语音质量及目标特征映射上都远远好于传统的基频转换算法。 This paper proposes an efficient morphing algorithm of pitch based on generalized artificial intelligence and the STRAIGHT model.The STRAIGHT model can modifies the pitch without loss of the quality of the voice.Moreover,based on GANN predictable ability,we can get the relationship between source and object,and realizes pitch conversion.Subjective evaluation and objective measurement indicate that the performance of the proposed method is better that that of the traditional method in term of synthesized quality and precision of mapping target characteristics.
作者 陈芝 张玲华
出处 《南京邮电大学学报(自然科学版)》 2010年第5期83-87,共5页 Journal of Nanjing University of Posts and Telecommunications:Natural Science Edition
基金 国家自然科学基金(60872105)资助项目
关键词 STRAIGHT模型 基频转换 人工神经网络 语音转换 STRAIGHT model pitch conversion GANN voice conversion
作者简介 陈芝(1984-),男,江苏盐城人。南京邮电大学信号与信息处理专业硕士研究生。研究方向为现代语音处理与通信技术。 张玲华(1964-),女,江苏淮安人。南京邮电大学通信与信息工程学院副院长、教授,博士。 通讯作者:张玲华 电话:(025)85881968 E-mail:zhanglh@njupt.edu.cn
  • 相关文献

参考文献11

  • 1KANA. High resolution voice conversion [ D ]. Portland, Oregon : Oregon Health and Science University,2001.
  • 2MATSUMOTO H, HIKI S, SONE T, et al. Multidimensional representation of personal quality of vowels and its acoustical correlates [J]. IEEE Trans Audio Electroacoust, 1973, AU-21 (5): 428 - 436.
  • 3FURUI S. Research on individuality features in speech waves and automatic speaker recognition techniques [ J ]. Speech communication, 1986,5 (2) : 183 - 197.
  • 4ITOH K, SAITO A. Effects of acoustical feature parameters of speech on perceptual identification of speaker [ J ]. IECE Trans, 1982, J65- A : 101 - 108.
  • 5KAWAHARA H. Speech representation and transformation using adaptive interpolation of weighted spectrum : Vocoder revisited [ C ] //Proc of IEEE Int Conf Acoust, Speech and Signal Processing. IEEE : Piscataway, 1997,2 : 1303 - 1306.
  • 6NARENDRABATH M. Transformation of fonnants for voice conversion using artificial neural networks [ J ]. Speech Communication, 1995,16(2) :207 -216.
  • 7LEE K S, DOH W,YOUN D H. Voice conversion using low dimensional vector mapping [ J ]. IEICE Transactions on Information & System,2002, E85 (D) : 1297 - 1305.
  • 8TURK O. New methods for voice conversion [ D ]. Istanbul, Bebek: Bogazici University ,2003.
  • 9ARSLAN L M. Speaker transformation algorithm using segmental codebooks (STASC) [ J ]. Speech Communication, 1999,28 ( 3 ) : 211 - 226.
  • 10ARSLAN L M, TALKIN D. Speaker Transformation Using Sentence HMM Based Alignments and Detailed Prosody Modification [ C ]// ICASSP IEEE Int Conf Acoust Speech Signal Process Proc. IEEE : Piscataway, 1998:289 - 292.

同被引文献11

  • 1左国玉,刘文举,阮晓钢.声音转换技术的研究与进展[J].电子学报,2004,32(7):1165-1172. 被引量:32
  • 2左国玉,刘文举,阮晓钢.一种使用声调映射码本的汉语声音转换方法[J].数据采集与处理,2005,20(2):144-149. 被引量:4
  • 3赵力.语音信号处理[M].北京:机械工业出版社,2008.
  • 4Stylianou Y. Voice transformation : a survey [ C ] HInternation Conference on Acoustics, Speech and Signal Processing. [ s1! 1. ]:[s. n. ] ,2009:3585-3588.
  • 5Nakamura K, Toda T, Saruwatari H, et al. Speaking- aid sys- tems using GMM-based voice conversion for electrolaryngeal speech [ J ]. Speech Communication, 2012,54 ( 1 ) : 134- 1 46.
  • 6Laskar R H ,Talukdar F A ,Bhattacharjee R,et al. Voice con- version by mapping the spectral and prosodic features usingsupport vector machine [ J ]. Applications of Soft Computing, 2009,58:519-528.
  • 7Kunikoshi A, Qian Yao, Soong F, et al. Improve FO modeling and generation in voice conversion [ C ]//IEEE International Conference on Acoustics, Speech and Signal Processing. [ s. 1. ] :[ s. n. ] ,2011:4568-4571.
  • 8Rao K S. Voice conversion by mapping the speaker-specific features using pitch synchronous approach [ J 1. Computer Speech and Language ,2010,24( 3 ) :474-494.
  • 9尹伟,易本顺.一种基于正弦激励的线性预测模型的语音转换方法[J].数据采集与处理,2010,25(2):218-222. 被引量:2
  • 10李燕萍,张玲华,丁辉.基于音素分类的汉语语声转换算法[J].南京邮电大学学报(自然科学版),2011,31(1):10-15. 被引量:1

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部