期刊文献+

高噪声背景下的语音识别系统设计 被引量:2

Realization of Speech Recognition System in Loud Ambient Noise
下载PDF
导出
摘要 文章讨论了高噪声背景下的汉语语音识别技术,从语音识别的一般方法出发,研究了基于半音节的半连续型隐马尔可夫模型(SCHMM)原理和算法,介绍了用DSP构建实现的方法,采用喉头送话器抑制了背景噪声,获得了较高的识别准确率。 A kind of Chinese speech recognition technology in loud ambient noise is discussed in this paper. Based on general speech recognition method, the principles and algorithms of semi-continuous Hidden Markov Model (SCHMM) are investigated. By introducing a throat MIC, the loud ambient noise is restrained, a higher recognition accuracy is achieved.
作者 刘萍 廖广锐
出处 《计算机与数字工程》 2009年第7期57-59,80,共4页 Computer & Digital Engineering
基金 "十五"国防预研基金资助课题
关键词 语音识别 隐马尔可夫模型 噪声 DSP 舰载指挥控制系统 speech recognition, hidden Markov model, noise, DSP, ship-based command and system
  • 引文网络
  • 相关文献

参考文献5

二级参考文献19

  • 1Du Limin, Feng Junlan, Song Yi, Sun Jinchen. A Chinese-English speech translation prototype system: CEST-CAS1.0.ICSPAT'99, Orlando, USA, 1999.
  • 2Du Limin, Feng Junlan, Song Yi, Wang Heng. Speech translation on internet CEST-CAS2.0. Proc. of ISIMP2001, Hong Kong,2001: 189- 192.
  • 3Rabiner L, Juang B H. Fundamentals of Speech Recognition.New Jersey, USA, Prentice Hall, 1993:350 - 352.
  • 4Ney H, Ortmanns S. Dynamic programming search for continuous speech recognition. IEEE Signal Processing Magazine, 1999, 16(5): 64 - 83.
  • 5Pascal W, Leon J. Using confidence measure and domain knowledge to improve speech recognition[A]. EuroSpeech[C]. 2003. 901~904,2713~2716.
  • 6Zhu X, Chen Y. Feature select in large vocabulary continuous speech recognition[A]. Proceedings of ICSP[C]. 2002. Si0223.
  • 7Fukuda, Nitta. Orthogonalized distinctive phonetic feature extraction for noise-robust automatic speech recognition[A]. IEICE Transactions on Information and Systems[C]. 2004.1110~1118.
  • 8Hiroya S, Honda M. Speaker adaptation method for acoustic-to-articulatory inversion using an HMM-based speech production model[A]. IEICE Transactions on Information and Systems[C].2004.1071~1078.
  • 9Zhao Junhui, Xie Xiang. Noise suppression based on auditory- like filters for robust speech recognition. In: Proc of International Conference of Signal Processing, Beijing: 2002. 560-563
  • 10Hermansky H, Morgan N. RASTA processing of speech. IEEE Transactions on Speech and Audio Processing, 1994,2 (4): 587-589

共引文献17

同被引文献18

  • 1孔建益,李公法,侯宇,杨金堂,蒋国璋,熊禾根.潜艇振动噪声的控制研究[J].噪声与振动控制,2006,26(5):1-4. 被引量:24
  • 2姚耀中,林立.潜艇机械噪声控制技术综述[J].舰船科学技术,2007,29(1):21-26. 被引量:12
  • 3查普曼.MATLAB[M].北京:科学出版社,1998.
  • 4Johnson G J, Thompson A M. Intermodulation in bridge detector amplifiers [ J ]. Proceedings of the lEE-Part C : Monographs, 1957,104 ( 5 ) :217 - 221.
  • 5边肇棋 张学工.模式识别[M].北京:清华大学出版社,2000..
  • 6谢虹.电子装备作战效能评估[J].航天电子对抗,1998,(3):57-59.
  • 7A. M. Martinez and A. C. Kak. PCA versus LDA[J].IEEE Trans. On Pattern Analysis and Machine Intelligence, 2001, 23(2) :228 233.
  • 8方开泰.实行多元统计分析[M].上海:华东帅范大学出版社.1986:54-71.
  • 9张璐琳,陈静.国军标(GJB4405A-2007)[J].语音通信干扰效果评定准则,2007.
  • 10LA Liporace. Maximum Likelihood for Multivariate Observa- tion of MarkovSouree. IEEE. Trans. IT[J]. 1982,28 (5): 729- 734.

引证文献2

二级引证文献3

相关主题

;
使用帮助 返回顶部