期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

汉语语音识别的抗噪性前端算法及性能分析 被引量：1

A Noise Robust Front End Algorithm for Mandarin Speech Recognition and Performance Analysis
在线阅读 下载PDF
导出
摘要 讨论了欧洲电信标准委员会ETSI提出的分布式语音识别系统的抗噪前端特征提取算法,该算法融合多种抗噪技术。结合汉语语音的特点,进行了汉语语音识别整体框架下的算法实现,并进行了实验和分析,典型噪声环境下的识别结果证明,相对于基线MFCC特征提取算法,稳健性有较大提高。 Noise robustness of automatic speech recognition system is the hot topic during recent years.In this paper,the noise robust Front End algorithm proposed by ETSI for Distributed Speech Recognition System(DSR)which is a combination of several separate noise-robust techniques is discussed.Considering Mandarin speech char-acters,a feature extraction system based on this algorithm is realized and analyzed its performance through recog-nition experiments is analyzed.In some typical noise environments,we got much higher recognition rate compared with classical MFCC(Melscale Frequency Cepstrum Coeffcient )feature is obtained.[
作者 林建臻 孙甲松 王作英
机构地区 清华大学电子工程系
出处 《电声技术》 北大核心 2004年第3期45-48,52,共5页 Audio Engineering
基金 犦国家863高技术项目(863-306-ZD03-02-1) 985重大项目(985校-22-攻关-06) 国家自然科学基金项目.
关键词 汉语 语音识别 抗噪性 性能分析 抗噪前端 特征提取算法 noise robustness DSR front end mandarin speech recognition
分类号 TN912.34 [电子电信—通信与信息系统]
  • 相关文献

参考文献11

  • 1王作英.基于段长分布的HMM语音识别模型[A]..第二届全国汉字语音识别会议[C].庐山,1989..
  • 2Satoru Tsuge, Toshiaki Fukada, Harald Singer. Speaker Normalized Spectral Subband Parameters For Noise Robust Recognition. ICASSP 1999.
  • 3Steven F. Boll. Suppression of Acoustic Noise in Speech Using Spectral Subtraction. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1979.
  • 4Agarwal A., Cheng Y.M.. Two-stage Mel-Warped Wiener Filter for Robust Speech Recognition. Proc.ASRU'99,1999.
  • 5Hynek Hermansky. Exploring Temporal Domain for Robustness in Speech Recognition. Invited paper, the 15th International Congress on Acoustics, 1995.
  • 6Agarwal A., Cheng Y. M.. Two-stage Mel-Warped Wiener Filter for Robust Speech Recognition. Proceeding of IEEE workshop on Automatic Speech Recognition and Understanding, Keystone, 1999.
  • 7Li Deng, Jasha Droppo, Alex Acero. A Bayesian Approach to Speech Feature Enhancement Using the Dynamic Cepstral Prior. ICASSP 2002.
  • 8Qi Li,Frank K.Soong, Olivier Siohan. An Auditory system-based feature for robust speech recognition. Eurospeech 2001.
  • 9Xiaodong Cui, Markus Iseli, Qifeng Zhu,Abeer Alwan. Evaluation of Noise Robust Features on the Aurora Databases. ICSLP 2002.
  • 10Ramalingam Hariharan, Imre Kiss, Olli Viikki. Noise Robust Speech Parameterization Using Multi-resolution Feature Extraction.IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2001-09.

共引文献3

同被引文献5

  • 1孙甲松,王作英,吴及.汉语语音识别中的有调拼音多候选问题[C]//第六届全国人际语音通讯学术会议论文集.深圳:中国计算机学会人工智能与模式识别专业委员会等6专业委员会,2001:243-247.
  • 2JELINEK F.Self-organized language modeling for speech recognition[M]. San Mateo: Readings in Speech Recognition, Morgan-Kaufmann, 1990 : 450-506.
  • 3BELLMAN R E. Dynamic programming[M].Princeton : Princeton University Press, 1957.
  • 4GUODONG Z, KIMTENG L. Interpolation of n-gram and mutual-information based trigger pair language models for Mandarin speech recognition[J]. Computer Speech and Language, 1999,13(2) : 125-141.
  • 5王作英,肖熙.基于段长分布的HMM语音识别模型[J].电子学报,2004,32(1):46-49. 被引量：42

引证文献1

二级引证文献1

电声技术
2004年 第3期

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