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

中文语音确认中子词置信度性能的研究 被引量：2

Investigation of Subwords Confidence Performance in Chinese Speech Verification
下载PDF
导出
摘要 本文提出了一种基于最小分类错误准则(MCE)的子词权重参数估计算法,通过MCE训练得到子词的权重系数。子词对词级置信度贡献量的研究表明:韵母的确认能力显著好于声母,在置信性能方面比声母更加稳定和可靠,区分能力优于声母。在130个关键词的关键词检测系统实验表明,采用不同子词贡献权重比等贡献权重时等错误率下降3.05%。 A Minimum Classification Error （MCE） criterion based subwords weighting parameters estimation algorithm is proposed in which the sub-word weighting parameters are derived by the MCE training. Investigation of the contribution of different sub-words on the word-level confidence measure show that Finals significantly outperform the Initials with more reliability and stability in confidence performance, and Finals have more discriminative power than those of Initials. Experiment on keyword spotting system with 130 keywords shows that the system with different sub-word weighting contribution achieved a relative Equal Error Rate （EER） reduction of 3.05% compared with the equal weighting contribution case.
作者 孙成立 刘刚 郭军
机构地区 北京邮电大学信息工程学院
出处 《中文信息学报》 CSCD 北大核心 2008年第2期106-109,128,共5页 Journal of Chinese Information Processing
基金 国家863计划资助项目(2006AA010102) 河北省科技厅资助项目(052135147,042135105) 河北省教育厅资助项目(2005340)
关键词 计算机应用 中文信息处理 语音确认 置信度 似然比检验 最小分类错误 computer application Chinese information processing utterance verification confidence measure likelihood ratio test MCE
分类号 TN391.42 [电子电信—物理电子学]
  • 相关文献

参考文献9

  • 1Chase I.in, Error Responsive Feedback Mechanisms for Speech Recognition. Ph.D. Thesis[D]. California,Carnegie Mellon University. April 1997.
  • 2F. Wessel, R. Schluter, K. Maeherey. Confidence measures for large vocabulary continuous speech recognition[A]. Proceeding of ICASSP[C]. 2001, 9(3):288-298.
  • 3E. Lleida, R.-C. Rose. Utterance verification in continuous speech recognition: decoding and training procedures[A]. Proceeding of ICASSP[C]. 2000. 8:126-139.
  • 4R. Sukkar, C. H. Lee. Vocabulary Independent Discriminative Utterance Verification for Non keyword Rejection in Sub-word Based Speech Recognition [A].Proceeding of ICASSP[C]. 1996. 4:420-429.
  • 5G. Bouwman, L. Boves, J. Koolwaaij. Weighting phone confidence measures for automatic speech recognition[A]. Proc. COST Action 249[C]. Ghent, Belgium. IEEE Press. 2000. 59-62.
  • 6S. Abdou, M. S. Scordilis. Beam search pruning in speech recognition using a posterior probability-based confidence measure[J]. Speech Communication, 2004, 42:409- 428.
  • 7B. H Juang, S. Katagiri. Discriminative learning for minimum error classification[J]. IEEE Transactions on Signal Processing. 1992, 40(12): 3043-3054.
  • 8李净,郑方,张继勇,吴文虎.汉语连续语音识别中上下文相关的声韵母建模[J].清华大学学报（自然科学版）,2004,44(1):61-64. 被引量：18
  • 9张家騄.汉语普通话区别特征系统树状图[J].声学学报,2006,31(3):193-198. 被引量：16

二级参考文献12

  • 1张家騄.汉语普通话区别特征系统[J].声学学报,2005,30(6):506-514. 被引量：26
  • 2Lee C-H, Rabiner L, Pieraccini R, et al. Acoustic modeling for large vocabulary speech recognition [J]. Computer Speech and Language, 1990, 4(2): 127-165.
  • 3Young S J, Woodland P C. Tree-based state tying for high accuracy acoustic modeling [A]. Proc ARPA Human Language Tech Workshop [C]. Plainsboro, NJ: Morgan Kaufmann Publisher, 1994, 307-312.
  • 4Reichl W, Chou W. Decision trees state tying based on segmental clustering for acoustic modeling [A]. Proc Int Conf Acoustics, Speech, Signal Processing'98 [C]. Seattle, Washington: IEEE Press, 1998. 801-804.
  • 5Reichl W, Chou W. Robust decision tree state tying for continuous speech recognition [J]. IEEE Trans Speech and Audio Proc, 2000, 8(5): 555-566.
  • 6曹剑芬.现代语音基础知识 [M].北京: 人民教育出版社,1990..
  • 7ZHENG Fang, SONG Zhanjiang, XU Mingxing. EASYTALK: A large-vocabulary speaker-independent Chinese dictation machine [A]. EuroSpeech '99 [C]. Budapest, Hungary: ISCA, 1999, 819-822.
  • 8Yong S, Kershaw D, Odell J, et al. The HTK Book [EB/OL]. http://htk.eng.cam.ac.uk, 2002.
  • 9Jakobson R, Fant G, Halle M. Preliminaries to speech analysis-the distinctive features and their correlates,Technical Report No.13, Acoustics Laboratory, MIT, reissued 1955.
  • 10Fant G, Lindblom B. Studies of minimal speech sound units. STL-QPSR, 1961:1-11.

共引文献31

同被引文献20

  • 1国玉晶,刘刚,刘健,郭军.基于环境特征的语音识别置信度研究[J].清华大学学报（自然科学版）,2009(S1):1388-1392. 被引量：8
  • 2Igor Szoke, Petr Schwarz, Pavel Matejka, et al. Phoneme based acoustics keyword spotting in informal continuous speech[C. In Proc. of RADIOELEKTRONIKA, Brno, Czech Republic,2005 : 302-309.
  • 3D. Veryri, I. Shafran, A. Stolcke, et al. The SRI/OGI 2006 spoken term detection system [ C J. In Proc. of In- terspeech, 2007 : 2393-2396.
  • 4O. Siohan, B. Ramabhadran, J. Mamou. The IBM 2006 spoken term detection system[ C 1. In Proc. NIST Spoken Term Detection Evaluation workshop ,2006.
  • 5Jiang Hui. Confidence measures for speech recognition: A survey[J]. Speech Communication,2005:455-470.
  • 6Jiang Hui. A Dynamic In-Search Data Selection Method With Its Applications to Acoustic Modeling and Utterance Verification[ J]. IEEE Transactions on Audio, Speech, and Language Processing,2005,13 ( 5 ) :945-955.
  • 7Jie Gao, Qingwei Zhao, Ran Xu and Yonghong Yan. Im- proved Lattice-based Confidence Measure for Speech Rec- ognition via a Lattice Cut off Procedure [ J ]. IEEE Com- puter Science,2009:473-476.
  • 8Frank Wessel, Ralf Schluter, Klaus Macherey, et al. Con- fidence Measures for Large Vocabulary Continuous Speech Recognition [ J ]. IEEE Transactions on Speech and Audio Processing,2001,9 (3) :288-298.
  • 9Atsunori Ogawa, Atsushi Nakamura. Discriminative Con- fidence And Error Cause Estimation For Extended Speech Recognition Function [ C ]. In: Proceedings of ICASSP, 2010:4454-4457.
  • 10Dong Wang, Javier Tejedor, Joe Frankel, et al. Posteri- or-Based Confidence Measures for Spoken Term Detection [ C ]. In : Proc. of ICASSP,2009:4889-4892.

引证文献2

二级引证文献1

中文信息学报
2008年 第2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