期刊文献+

改进的GMM模型语声转换系统 被引量:2

A Modified Method for Voice Conversion Based on GMM
下载PDF
导出
摘要 传统的基于GMM模型线性语音转换系统在语音转换阶段,由于转换函数的概率加权组合使合成语音共振峰带宽变宽,谱包络过于平滑。文中提出依据后验概率大小和前后语音的相关性,选择部分转换分量函数进行语音转换。实验表明不仅简化了语音转换,而且经过转换的语音质量也有一定的提高,对语音的实时转换有重要的意义。  For the traditional GMM-based linear voice conversion system,due to the probability weighted combination of conversion function,the resonant peak width of composite voice is broaden and the spectral envolop is flat.The autors propose to convert voice using partral conversion component function according to posterior probability and correlation of adjacent voice signals.The experiments have prove that the voice conversion is simplified and the converted voice quality is improved.It is important for real-time conversion of voice.
出处 《南京邮电大学学报(自然科学版)》 2007年第5期11-15,21,共6页 Journal of Nanjing University of Posts and Telecommunications:Natural Science Edition
基金 江苏省"青蓝工程"基金(QL003YZ)资助项目
关键词 语音处理 语声转换 韵律转换 高斯混合模型 Speech processing Voice conversion Prosody modification Gaussian mixture model
  • 相关文献

参考文献11

  • 1ABE M, NAKAMURA S, SHIKANO K, et al. Voice Conversion through Vector Quantization [ C ]//IEEE Proceedings of ICASSP. New York, 1988:565 - 568.
  • 2VALBRET H, MOULINES E, TUBACH J P. Voice transformation using PSOLA technique [ J ]. Speech Communication, 1992,11 (6) : 175 - 187.
  • 3NARENDRANNATH M, MURTHY H, RAJENDRAN S. Transformation of formants for voice conversion using artificial neural networks [J]. Speech Communication, 1995, 16(2): 207- 216.
  • 4STYLIANOU Y, CAPPE O, MOULINES E. Continuous Probabilistic Transform for Voice Conversion [ J ]. IEEE Trans on Speech and Audio Processing, 1998,6 (2) : 131 - 142.
  • 5YE H, YOUNG S. High quality voice morphing [ C ]//ICASSP. 2004 :I9 - I12.
  • 6REYNOLDS D A, ROSE R C. Robust text-independent speaker identification using Gaussian mixture speaker models [ J ]. IEEE Trans on Speech Audio Process, 1995,3 ( 1 ) :72 - 83.
  • 7ARSLAN L M. Speaker Transformation Algorithm using Segmental Codebooks [ J ]. Speech Communication, 1999,28 (3) :211 - 226.
  • 8KAIN A, MACON M W. Spectral voice conversion for text - tospeech synthesis [ C ]//ICASSP. Seattle, Wa, 1998:285 - 289.
  • 9ATHANASIOS M, SHRIKANTH S. Narayanan K. Multichannel audio Synthesis by Subband-Based Spectral Conversion and Parameter Adaptation [ J ]. IEEE Trans on Speech and Audio Processing, 2005,13 (2) :263 - 274.
  • 10RabinerL JuangBH.Fundamentals of speech recognition[M].北京:清华大学出版社,1999.200-240.

共引文献4

同被引文献20

引证文献2

二级引证文献9

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