期刊文献+

利用声调提高中文连续数字串语音识别系统性能 被引量:3

Improving the Performance of Continuous Mandarin Digit String Recognition System by Using Tones
下载PDF
导出
摘要 采用平均幅度差法、自相关函数法和简单逆滤波器跟踪法相结合的方法计算语音信号的基音频率.根据声调模式的不同,采用基于规则的方法对声调进行识别,对连续数字串识别中一些易混淆的数字对进行区分,从而达到提高数字串识别系统性能的目的. According to the extracted pitch curve, it can discriminate between four Mandarin tones. A composite algorithm for pitch extraction was promoted which integrates AMDF, auto correlation and simple inverse filtering trucking (SIFT) algorithm by using some rules. In the Mandarin continuous digit string recognition system, the tones are used to discriminate some confusing digit pairs, which can improve the system's recognition rate.
出处 《上海交通大学学报》 EI CAS CSCD 北大核心 2004年第2期185-188,共4页 Journal of Shanghai Jiaotong University
基金 上海市科学技术委员会基础研究基金(01JC14033) 美国贝尔实验室上海分部资助项目
关键词 语音识别 声调 数字识别 Computer simulation Correlation methods
  • 相关文献

参考文献7

  • 1[1]Zhang J S, Hirose K. Anchoring hypothesis and its application to tone recognition of Chinese continuous speech acoustics [A]. Proc IEEE Int Conf Acoust,Speech, Signal Processing [C]. Istanbul, Turkey:ICASSP, 2000. 1419-1422.
  • 2[2]u Y, Hemmi K, Inoue K. A tone recognition of polysyllabic Chinese words using an approximation model of four tone pitch patterns[A]. Proc Industrial Electronics, Control and Instrumentation Proceeding[C]. Asilomar, Califormia, USA: IECON,1991. 2115-2119.
  • 3[3]Zhang G L, Zheng F, Wu W H. Tone recognition of Chinese continuous speech[A]. International Symposium on Chinese Spoken Language Processing[C].Beijing: ISCSLP, 2000. 207-210.
  • 4[4]Kobayashi H, Shimamura T. A weighted autocorrelation method for pitch extraction of noisy speech[A]. Proc IEEE Int Conf Acoust, Speech, Signal Processing[C]. Istanbul, Turkey: ICASSP, 2000.1307- 1310.
  • 5[5]Hemandez D H, Huici M E, Lorenzo G J. Combined algorithm for pitch detection of speech signals [J].Electronics Letters, 1995, 31 ( 5 ): 15 - 16.
  • 6[6]Samad S A, Hussain A, Low K F. Pitch detection of speech signals using the cross correlation technique[A]. Intelligent Systems and Technologies for the Next Millenium[C]. Kuala Lumpur Malaysia: TENCON, 2000. 283-286.
  • 7[7]Cherif A. Pitch and formants extraction algorithm for speech processing[A]. Proc IEEE Int Conf Electronics, Circuits and Systems[C]. Kaslik, Lebanon:ICECS, 2000. 595-598.

同被引文献39

  • 1王韫佳.音高和时长在普通话轻声知觉中的作用[J].声学学报,2004,29(5):453-461. 被引量:33
  • 2[英]克里斯特安尼,等(著).李国正,王猛,曾华军(译).支持向量机导论[M].北京:电子工业出版社,2004.
  • 3顾明亮,夏玉果,王劲松.噪声环境下的汉语声调识别[J].计算机技术与发展,2007,17(8):70-72. 被引量:2
  • 4王欢良,钱瑶,F.K.Soong,韩纪庆.基于声调建模的带噪汉语数字串语音识别[J].声学学报,2007,32(5):454-460. 被引量:2
  • 5Huang C H, Side F. Pitch tracking and tone features for mandarin speech recognition. Proceedings of the 25th International Conference on Acoustics, Speech and Signal Processing, Istanbul, Turkey, 2000; 3:1523-1526
  • 6Lei X, S M, Hwang M, Ostendorf M et al. Improved tone modeling for mandarin broadcast news speech recognition. In: Proceedings of Interspeech (ICSLP), Pittsburgh, USA, 2006:1277-1280
  • 7Wang H L, Qian Y, Soong F K, Zhou J L et al. Improved Mandarin Speech Recognition by Lattice Rescoring with Enhanced Tone models. In: Proceedings of International Symposium on Chinese Spoken Language Processing, 2006: 445-443
  • 8Yang W J, Lee J C, Chang Y C et al. Hidden Markov Model for Mandarin lexical tone recognition. IEEE Trans. on Acoustic Speech and Signal Processing, 1988; 36(7): 988-992
  • 9Thubthong N, Kijsirikul B, Tone recognition of continuous Thai speech under tonal assimilation and declination effects using half-tone model. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 2001; 9(6): 815-825
  • 10CAO Yang, ZHANG Shu Wu, HUANG Tai Yi et al. Tone modeling for continuous Mandarin speech recognition. International Journal of Speech Technology, 2004; 7(2-3): 115-128

引证文献3

二级引证文献2

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