期刊文献+

一种新的共振峰参数提取算法及在语音识别中的应用 被引量:3

A Formant Extraction Algorithm and Its Application in Speech Recognition
下载PDF
导出
摘要 采用了一种基于逆滤波器原理的方法来识别共振峰参数。用一组逆滤波器来逼近语音信号的短时能谱,通过动态搜索算法可以得到滤波器组中各个滤波器的位置与带宽,从而确定了共振峰的位置和带宽。采用了优化动态搜索的算法,提高了运算速度。把共振峰作为特征参数用于一个小词汇量的汉语语音识别系统中,识别正确率达到了98%。 A bank of inverse filters is used to approach the STFT of speech signal. The dynamic programming algorithm searches the optimum locations and bandwidths of the filter bank, so that the location and bandwidth of the filter (also the formant) is specified. The formant and corresponding bandwidth parameters result in a correct recognition rate of 98% in a small vocabulary mandarin speech recognition system.
出处 《计算机工程》 CAS CSCD 北大核心 2003年第13期67-68,共2页 Computer Engineering
基金 上海市科学技术委员会基础研究项目(01JC14033)
关键词 共振峰 语音识别 逆滤波器 动态搜索算法 Formant Speech recognition Inverse filter
  • 相关文献

参考文献4

  • 1Zhao Qifang, Shimamura T, Suzuki J. A Robust Algorithm for Formant Frequency Extraction of Noisy Speech. Circuits and Systems. ISCAS '98, Proceedings of the 1998 IEEE International Symposium on. 1998.5:534-537.
  • 2Vuckovic V, Stankovic M. Formant Analyzes and Vowel Classification Methods. Telecommunications in Modem Satellite, Cable and Broadcasting Service. TELSIKS 2001, 5th International Conferenceon. 2001,1:21-24.
  • 3Watanabe A. Formant Estimation Method Using Inverse-filter Control. Speech and Audio Processing, IEEE Transactions on, 2001,9(4):317-326.
  • 4Lee I, Gibson J D. Robust Backward Adaptive Formant Prediction for Speech Coder. Electronics Letters, 1998,34(24):2314 -2315.

同被引文献60

引证文献3

二级引证文献42

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