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

蒙古文字母到音素转换方法的研究 被引量：4

Research on grapheme to phoneme conversion for Mongolian
下载PDF
导出
摘要 针对蒙古文字母到音素的转换(grapheme to phoneme conversion,G2P)问题,提出了基于规则的蒙古文G2P转换方法和基于联合序列模型的蒙古文G2P转换方法。实验结果表明,利用联合序列模型的蒙古文G2P转换方法要明显好于基于规则的蒙古文G2P转换方法。并且建立的基于联合序列模型的蒙古文G2P转换系统的词误识率为16.32%,音素误识率仅为3.37%,能达到实用要求。 This paper presented the rule-based Mongolian G2P conversion method and the statistic-based Mongolian G2P conversion method for Mongolian G2P conversion.Experimental results show that Mongolian G2P conversion method based on the joint-sequence model is significantly better than the rule-based Mongolian G2P conversion method.The word error rate is 16.32% and the phoneme error rate is 3.37% for the Mongolian G2P conversion system based on the joint-sequence model,and this system has reached the application requirements.
作者 飞龙 高光来 闫学亮
机构地区 内蒙古大学计算机学院
出处 《计算机应用研究》 CSCD 北大核心 2013年第6期1696-1700,共5页 Application Research of Computers
基金 国家自然科学基金资助项目(61263037 71163029) 内蒙古自然科学基金重大资助项目(2011ZD11)
关键词 蒙古文 字母到音素的转换 联合序列模型 联合多元 联合分割 Mongolian grapheme-to-phoneme conversion（G2P） joint-sequence models joint multigram co-segmentation
分类号 TP391.1 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献12

  • 1MENG H M, SENEFF S, ZUE V W. Phonological parsing for bi-directional letter-to-sound / sound-to-letter generation [ C ]//Proc of Workshop on Human Language Technology. 1994: 289-294.
  • 2TORKKOLA K. An efficient way to learn English grapheme-to-phoneme rules automatically[ C ]//Proc of IEEE International Conference on Acoustics, Speech, and Signal Processing. 1993:199-202.
  • 3BAGSHAW P C. Phonemic transcription by analogy in text-to-speech synthesis: novel word pronunciation and lexicon compression [ J ]. Computer Speech & Language, 1998,12 ( 2 ) : 119-142.
  • 4MENG H. A hierarchical lexical representation for bi-directional spelling-to-pronunciation/pronunciation-to-spelling generation [ J ]. Speech Communication,2001,33(3) : 213-239.
  • 5BISANI M, NEY H. Muhigram-based graphenae-to-phoneme conversion for LVCSR [ C ]//Proc of INTERSPEECH. 2003 : 933- 936.
  • 6BELLEGARDA J R. Unsupervised, language-independent grapheme- to-phoneme conversion by latent analogy[ J]. Speech Gommunieation ,2005,46 (2) : 140-152.
  • 7WANG Dong. Out-of-vocabulary spoken term detection [ D ]. Edinburgh : University of Edinburgh. 2010.
  • 8TAYLOR P. Hidden Markov models for grapheme to phoneme conversion[ C ]//Proc of INTERSPEECH. 2005 : 1973-1976.
  • 9BISANI M, NEY H. Joint sequence models for grapheme-to-phoneme conversion [ J]. Speech Communication ,2008,50 ( 5 ) :434-451.
  • 10BAO Fei-long, GAO Guang-lai. Improving of acoustic model for the mongolian speech recognition system [ C ]//Proc of Chinese Conference on Pattern Recognition. 2009: 616-620.

同被引文献11

  • 1Feilong Bao, Guanglai Gao. The Research on Mongo- lian Spoken Term Detection Based on Confusion Net- work[C]//Proceedings of the Chinese Conference on Pattern Recognition (CCPR2012). Beijing, 2012 ; 606- 612.
  • 2Feilong Bao, Guanglai Gao. Improving of Acoustic Model for the Mongolian Speech Recognition System [C]//Proceedings of the Chinese Conference on Pat tern Recognition (CCPR2009). Nanjing, 2009: 616- 620.
  • 3Feilong Bao, Guangiai Gao, Xueliang Yan. Segmenta- tion-based Mongolian LVCSR Approach[C]//Proeeed ings of the 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP2013), Van- couver, 2013.. 8136-8139.
  • 4J Mamou, B Ramabhadran and O Siohan. Vocabulary independent spoken term detection[C]//Proceedings of the ACM-SIGIR'07. Amsterdam, 2007..615-622.
  • 5Ville T. Turunen and Mikko Kurimo, Indexing Confu-sion Networks for MorPh-based Spoken Document Re- trieval [C]//Proceedings of the ACM-SIGIR'07. Am- sterdam, 2007 : 631-638.
  • 6D Wang. Out-of-vocabulary spoken term detection IDa. Ph.[ D]. dissertation University of Edinburgh. 2010.
  • 7G Gosztolya and L Toth. Spoken term detection based on the most probable phoneme sequence[C]//Proceed- ings of the 2011 International Symposium on Applied Machine Intelligence and Informatics ( SAMI ) (IEEE), Slovakia, 2011 : 101-106.
  • 8L Mangu, E Brill, and A Stolcke: Finding consensus in speech recognition: word error minimization and other applications of confusion networks [J]. Comput- er Speech and Language, 2000, 14(4): 373-400.
  • 9Young S, et al. The HTK book (Revised for HTK version 3.4.1)[M]. Cambridge University. 2009.
  • 10A Stolcke. SRILM--An Extensible Language Model- ing Toolkit[C]//Proceedings of Intl. Conf. Spoken Lantguage Processing. Denver, Colorado,2002.

引证文献4

二级引证文献1

计算机应用研究
2013年 第6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