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

语种辨识的多特征信息应用 被引量：2

Application of multiple speech features to language identification
下载PDF
导出
摘要 提取动态的高层语言学特征建立了改进的语种相关的、联合的GMM-LM语种辨识方案。该方案减小了不同语种的高斯混合模型和语言模型之间的相关性,也降低了训练的复杂度。还提出了基于特征提取层和判决层融合技术的语种辨识系统。该系统利用了不同类型的特征对区分不同语种的贡献来增加不同语种语料之间的差异,并使相同语种的语料之间的差异减小。实验表明,设计的语种辨识系统具有较好的扩展性;基于特征提取层和判决层的融合系统能够有效地提高系统识别率。 Dynamic high-level language cues are extracted to build the language-dependent and combined GMM-LM language identification system which decreases the correlation between Gaussian Mixture Model and Language Model.It also reduces the training complexity.The feature-level and decision-level multiple features fusion is proposed to the GMM-LM system which distinguishes multiple languages using different feature cues.This system can maximize the speech diversity of different languages and minimize the speech diversity of same languages.It concludes that this modified Gaussian Mixture Model recognizer followed by Language Model has better system expansibility; meanwhile the fusion systems based on feature-level and decision-level can get better performance.
作者 曾秀花 杨鉴 徐永华
机构地区 曲靖师范学院物理与电子工程学院 云南大学信息学院
出处 《计算机工程与应用》 CSCD 北大核心 2010年第25期146-148,152,共4页 Computer Engineering and Applications
基金 国家自然科学基金No.60865002~~
关键词 语种识别 高斯混合模型 特征融合 language recognition Gaussian mixture model feature fusion
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献16

  • 1Martin A F, Przybocki M A.NIST 2003 language recognition evaluation[C]//Proceedings of Eurospeech, 2003 : 1341-1344.
  • 2Zissman M A.Comparison of four approaches to automatic language identification of telephone speech[J].IEEE Transactions on Speech and Audio Processing,1996,4:31-44.
  • 3Torres-Carrasquillo P A.Approaches to language identification using Ganssian mixture models and shifted delta cepstral features[C]//International Conference on Spoken Language Processing, Denver, 2002: 82-92.
  • 4Rabiner L R.On the use of autocorrelation analysis for pitch deteetion[J].IEEE Transactions on Acoustic, Speech, and Signal Processing, 1977,25 ( 1 ).
  • 5Adami A, Mihaescu R, Reynolds D A,et al.Modeling prosodic dynamics for speaker recognition[C]//International Conference on Acoustics, Speech and Signal Processing, Hong Kong, 2003: 788-791.
  • 6Adami A, Hermansky H.Segmentation of speech for speaker and language recognition[C]//Processing Eurospeech,2003 : 841-844.
  • 7Kishore S P, Krishna A V.Forrnant extraction using difference spectrum[EB/OL]. ( 2004 ) .http ://ravi.iiit.ac.in/-speech/publications/ reports/formants.pdf.
  • 8毕福昆 杨鉴 杨桃香.基于最优声学特征子集的语音情感识别.仪器仪表学报,2007,28(4).
  • 9Torres-Carrasquillo P A,Reynolds D A, Jr Deller J R.Language identification using Gaussian mixture model tokenization[C]// ICASSP, Orlando, Fl, USA, 2002.
  • 10Gleason T P, Zissman M A.Composite background models and score standardization for language identification systems[C]// ICASSP 2001,1:529-532.

二级参考文献22

  • 1侯精一．现代汉语方言音库[M]．上海：上海教育出版社，1994—1999．
  • 2Tsai Wuei-He, Chang Wen-Whe. Discrimination Training of Guassian Mixture Bigram Models with Application to Chinese Dialect Identification[J] . Speech Communication 2002,36 : 317-326
  • 3Lim Boon Pang,Li Haizhou,Ma Bin. Using Local & Global Phonotactic Features in Chinese Dialect Identification [C]. In: Proc.of ICASSP'05,2005,1 : 577 -580
  • 4Muthusamy Y K,Barnard E,Cole R A. Reviewing automatic language identification [C]. IEEE Signal Processing Mag, 1994, 11(4):33-3
  • 5Zissman M A. Comparison of Four Approaches to Automatic Language Identification of Telephone Speech [C]. IEEE Trans.Speech and Audio Pro, 1996,4(1):31-34
  • 6Torres-Carrasquillo P A, Reynolds D A, Deller J R Jr. Language identification using Gaussian mixture model tokenization [C]. In:Proc. of ICASSP 2002,12002 : 757- 760
  • 7Laird N M, Lange N, Stram D. Maximum Likelihood Computations with Repeated Measures: Applications of the EM algorithm[J]. Journal of the American Statistical Association, 1987,82:97-105
  • 8Jelinek F. Statistical Methords for Speech Recognition [M]. Cambridge, Massachusetts,MIT Press,1999
  • 9Biederman D C, Ososanya E. Capacity of several neural networks with respect to digital adder and multiplier System Theory [C]. In: Proc. of the Twenty-Seventh Southeastern Symposium on Neural Network, 1995. 305-308
  • 10赵力．语音信号处理[M]．北京：机械工业出版社，2001

共引文献2

同被引文献17

  • 1戴冠男,王炳锡,屈丹.基于C_nV结构的自动语言辨识研究[J].计算机工程与应用,2006,42(23):173-175. 被引量：2
  • 2李思一,戴蓓蒨,王海祥.基于子带GMM-UBM的广播语音多语种识别[J].数据采集与处理,2007,22(1):14-18. 被引量：2
  • 3Rouas J L, Farinas J, Pellegrino E Automatic modeling of rhythm and intonation for language identification[C]// Proceedings of the 15th ICPhS. Berlin, Germany: Springer, 2003: 326-339.
  • 4Guijarrubia V G, Torres M I. Text-and speech-based phonotactic models for spoken language identification of Basque and Span- ish[J]. Pattern Recognition Letters, 2010, 31(1): 523-532.
  • 5Nagarajan T, Murthy H A. Language identification using acous- tic log-likelihoods of syllable-like units[J]. Speech Communi- cation, 2006, 48(5): 913-926.
  • 6Zuo L B, Yang J, He L Y. Language identification of minority language based on GMM-UBM model[C]//Proceedings of 2010 International Conference on Circuit and Signal Processing. Pis- cataway, NJ, USA: IEEE, 2010: 428-436.
  • 7Rouas J L, Farinas J, Pellegrino F, et al. Rhythmic unit ex- traction and modeling for automatic language identification[J]. Speech Communication, 2005, 47(1): 436-456.
  • 8Torres-Carrasquillo P A, Reynolds D A, Deller J R. Lan- guage identification using Gaussian mixture model Tokeniza- tion[C]//Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Piscataway, NJ, USA: IEEE, 2002: 42-35.
  • 9阿孜古丽阿布力米提.维吾尔语基础教程[M].北京:中央民族大学出版社,2006.
  • 10李晓阳,伊.达瓦,吾守尔.斯拉木,勾坂芳典.基于GMM-UBM/SVM的维吾尔语电话语音监控系统[J].计算机应用与软件,2012,29(1):46-48. 被引量：2

引证文献2

二级引证文献2

计算机工程与应用
2010年 第25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