期刊文献+

基于语音频谱包络抽取的MFCC算法 被引量:4

An Algorithm for MFCC Based on Speech Spectrum Harmonic Samples Extraction
下载PDF
导出
摘要 MFCC可以更加准确地表示语音低频处的频谱包络,在语音转换中是一种很好的频谱包络表示方法;提出一种新的有效的求解MFCC的算法,先对频谱通过谐波抽取得到阶梯谱包络,再对阶梯谱包络进行Mel尺度变换,最后通过余弦变换求得MFCC参数。该方法实现简单,运算结果准确。 MFCC can express speech spectrum more accurately at low frequency, so MFCC is a good method to express the spectral envelope in voice conversion; A new and efficient algorithm for MFCC is proposed. At first, the staircase envelope is obtained through harmonic extraction, then the staircase envelope is transformed by Mel frequency scale, at last the MFCC coefficients are extracted by cosine transformation. The algorithm can be realized easily, and the result is good.
出处 《国防科技大学学报》 EI CAS CSCD 北大核心 2004年第4期42-45,共4页 Journal of National University of Defense Technology
关键词 语音处理 MFCC 语音识别 说话人识别 语音转换 speech processing MFCC speech recognition speaker recognition voice conversion
  • 相关文献

参考文献6

  • 1Madlová A. Autoregressive and Cepstral Parametrization in Harmonic Speech Modeling[J]. Journal of Electrical Engineering, 2002, 53(1):46-49.
  • 2Stylianou Y. Harmonic Plus Noise Models for Speech, Combined with Statistical Methods, for Speech and Speaker Modification[D]. Ph.D. thesis, école Nationale Supèrieure des Télécommunications, Paris, France,January 1996.
  • 3Tanaka K, Abe M. A New Fundamental Frequency Modification Algorithm with Transformation of Spectrum Envelope According to F0[C]. ICASSP 1997, 2: 951-954.
  • 4邵央,刘丙哲,李宗葛.基于MFCC和加权矢量量化的说话人识别系统[J].计算机工程与应用,2002,38(5):127-128. 被引量:34
  • 5Li Bo, Li Ying-ying, Wang Cheng-you, Liu Yun-hui, Tang Chao-jing, Zhang Er-yang. A New Efficient Pitch-Tracking Algorithm[C]. Proceedings of the 2003 IEEE International Conference on Robotics, Intelligent Systems and Signal Processing,Changsha, China,Oct. 2003:1102-1107.
  • 6Tokuda K, Kobayashi T, Imai S. Recursive Calculation of Mel-cepstrum from LP Coefficients[R]. http://kt-lab.ics.nitech.ac.jp /~tokuda/tips/mgceptrsa2.pdf.

共引文献33

同被引文献25

引证文献4

二级引证文献15

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