期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

语音转换中系统单位冲激响应的频谱搬移方法研究

Research of Spectrum Modification Based on System Unit Impulse Function in Voice Conversion
下载PDF
导出
摘要 频谱包络转换是语音转换中的一项重要内容,基于双线性转换函数进行频谱搬移的方法可以有效地进行谱包络转换,而且在基于小语料库进行训练时仍能得到稳定的转换谱包络。本文基于LPC分析,提出用反傅里叶变换的方法来求解频谱搬移后的系统单位冲激响应,以此来实现频谱包络的变换,并取得了较好的效果。 Spectral envelope conversion is an important content of voice conversion. Based on bilinear transform function,spectral envelope can be efficiently converted even with small training speech database. In this thesis,based on LPC analysis,a method for calculating the spectrum converted system unit impulse function is proposed. So the spectral envelope is converted efficiently.
作者 陆静芳 李波 王成友
机构地区 国防科学技术大学电子科学与工程学院
出处 《现代电子技术》 2005年第24期40-42,48,共4页 Modern Electronics Technique
关键词 语音转换 频谱包络转换 小语料库 LPC voice conversion spectral envelope conversion small training speech database LPC
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献15

  • 1Abe M,Nakamura S,Shikano K,et al.Voice Conversion Through Vector Quantization,ICASSP,1988.655-658
  • 2Arslan L M.Speaker Transformation Algorithm UsingSegmental Codebooks(STASC)[J].Speech Communication,1999,28(3): 211226.
  • 3Baudoin G,Stylianou Y.On the Transformation of theSpeech Spectrum for Voice Conversion.In Proceedings of ICSLP′96,Philadelphia,PA,October 1996,2:1 405-1 408.
  • 4Chen Y N,Chu M,Chang E,et al.Voice Conversion with Smoothed GMM and MAP Adaptation.Euro-speech 2003-GENEVA.2 4132 416.
  • 5Duxans H,Bonafonte A,Kain A,et al.Including Dynamicand Phonetic Information in Voice Conversion Systems.In Inter-speech2004:1 193-1 196.
  • 6Iwahashi N,Sagisaka Y.Speech Spectrum Conversion Basedon Speaker Interpolation and Multi-functional Representation with Weighting by Radial Bases Function Networks[J].Speech Communication,1995,16(2):319-326.
  • 7Kain A.High Resolution Voice Transformation,Ph.D.Dissertation,OGI School of Science and Engineering at Oregon Health and Science University,October 2001.
  • 8Mizuno H,Abe M.Voice Conversion Algorithm Based onPiecewise Linear Conversion Rules for Formant Frequencies and Spectrum Tilt[J].Speech Communication,1995,16(2):125-126.
  • 9Narendranath M,Murthy H A,Rajendran S,et al.Transformation of Formants for Voice Conversion Using Artificial Neural Networks[J].Speech Communication,1995,16(2):207-216.
  • 10Rentzos D,Vaseghi S,Yan Q,et al.Voice ConversionThrough Transformation of Spectral and Intonation Features.ICASSP,2004,I-21-24.

二级参考文献26

  • 1初敏.韵律研究与合成语音的自然度[A].第五届全国现代语音学学术会议.新世纪的现代语音学[C].北京: 清华大学出版社,2001.295-301.
  • 2VERHELST W, MERTENS J. Voice conversion using partitions of spectral feature space[A]. ICCASSP[C]. Atlanta USA, 1996.365-368.
  • 3LEE K S, DOH W, YOUN D H. Voice conversion using low dimensional vector mapping[J]. IEICE Trans Inf & Syst, 2002, E85-D(8):1297-1305.
  • 4MIZUNO H, ABE M. Voice conversion algorithm based on piecewise linear conversion rules for formant frequencies and spectrum tilt[J]. Speech Communication, 1995, 16(2): 153-164.
  • 5NARENDRANATH M, MURTHY H A, RAJENDRAN S. Transformation of formants for voice conversion using artificial neural networks[J]. Speech Communication, 1995, 16(2): 207-216.
  • 6TURK O. New methods for voice conversion. Master Degree Thesis of Science[D]. Bogazici University, 2003.
  • 7ABE M, NAKAMURA S, SHIKANO K, et al. Voice conversion through vector quantization[A]. ICASSP [C]. New York, 1988.655-658.
  • 8ABE M. A segment-based approach to voice conversion[A]. ICASSP[C].Toronto, Canada, 1991. 765-768.
  • 9KAIN A. High Resolution Voice Transformation[D]. OGI School of Science and Engineering at Oregon Health and Science University, 2001.
  • 10STYLIANOU Y. Harmonic Plus Noise Models for Speech, Combined with Statistical Methods, for Speech and Speaker Modification[D]. Ecole Nationale Superieure des Telecommunications, Paris, France, 1996.

共引文献33

现代电子技术
2005年 第24期

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