一级黄色片免费播放|中国黄色视频播放片|日本三级a|可以直接考播黄片影视免费一级毛片

高級搜索

留言板

尊敬的讀者、作者、審稿人, 關(guān)于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復(fù)。謝謝您的支持!

姓名
郵箱
手機號碼
標(biāo)題
留言內(nèi)容
驗證碼

似然得分歸一化及其在與文本無關(guān)說話人確認中的應(yīng)用

鄧浩江,  杜利民,  萬洪杰

鄧浩江, 杜利民, 萬洪杰. 似然得分歸一化及其在與文本無關(guān)說話人確認中的應(yīng)用[J]. 電子與信息學(xué)報, 2005, 27(7): 1025-1029.
引用本文: 鄧浩江, 杜利民, 萬洪杰. 似然得分歸一化及其在與文本無關(guān)說話人確認中的應(yīng)用[J]. 電子與信息學(xué)報, 2005, 27(7): 1025-1029.
Deng Hao-jiang, Du Li-min, Wan Hong-jie. Likelihood Score Normalization and Its Application in Text-Independent Speaker Verification[J]. Journal of Electronics & Information Technology, 2005, 27(7): 1025-1029.
Citation: Deng Hao-jiang, Du Li-min, Wan Hong-jie. Likelihood Score Normalization and Its Application in Text-Independent Speaker Verification[J]. Journal of Electronics & Information Technology, 2005, 27(7): 1025-1029.

似然得分歸一化及其在與文本無關(guān)說話人確認中的應(yīng)用

Likelihood Score Normalization and Its Application in Text-Independent Speaker Verification

  • 摘要: 該文研究了似然得分歸一化方法的原理,建立了基于自適應(yīng)GMM模型的說話人確認系統(tǒng),并將非特定人的背景模型與特定人的cohort模型相結(jié)合,提出了混合歸一化的方法。在電話語音條件下,該文比較了不同得分歸一化方法對確認系統(tǒng)性能的影響。實驗表明,在自適應(yīng)GMM模型似然比得分的基礎(chǔ)上,T-cohort與通用背景模型混合歸一化能獲得最佳識別效果。當(dāng)錯誤拒絕率為5%時,該方法可以獲得0.5%的錯誤接受率,遠遠低于采用通用背景模型歸一化方法的2%。
    Abstract: In this paper, the methodology of likelihood score normalization is studied. The text-independent speaker recognition system based on the adapted Gaussion Mixture Models(GMMs) is established, and the approach to normalize scores combining speaker-independent background model and the speaker-dependent models of cohort speaker sets are proposed. The speaker verification experiments over telephone channels show that based on the likelihood ratio of adapted GMMs system, both cohort normalization and hybrid score normalization approaches can improve the verification performance of baseline system using Universal Background Model (UBM). Specially, the hybrid approach combining UBM and cohort models selected during testing (T-cohort normalization) achieve the best performance. At a miss probability of 5%, the hybrid approach using UBM and T-cohort models reduce the false alarm rate to 0.5% compared to 2% for the baseline.
    • HTML全文
  • Doddington G R, Przybocki M A, Martin A F, Reynolds D A. The NIST speaker recognition - Overview, methodology, systems,results, perspective[J].Speech Communication.2000, 31(2- 3):225-[2]Reynolds D A. The effects of handset variability on speaker recognition performance: experiments on the switchboard corpus.In: Proc. ICASSP-1996, Atlanta, USA, May 1996:113 - 116.[3]Heck L P, Weintraub M. Handset dependent background models for robust text-independent speaker recognition. In: Proc.ICASSP-1992, Munich, Germany, 1997:1071 - 1074.[4]Reynolds D A, Quatieri T F, Dunn R B. Speaker verification using adapted Gaussian mixture models[J].Digital Signal Processing.2000, 10(1 - 3):19-[5]Dunn R B, Reynolds D A, Quatieri T F. Approaches to speaker detection and tracking in conversational speech[J].Digital Signal Processing.2000, 10(1 - 3):93-[6]Ariyaeeinia A M.[J].Sivakumaran P. Analysis and comparison of score normalization methods for text-dependent speaker verification. In Proc. EUROSPEECH97, Rhodes, Greece.1997,:-[7]Rosenberg A E, et al.. The use of cohort normalized scores for speaker verification. In Proc. ICSLP-1992, Banff, Canada, Nov.1992:599 - 602.[8]Colombi J, Ruck D, Rogers S, Oxley M, Anderson T. Cohort selection and word grammar effects for speaker recognition. In Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing,Atlanta, GA, 1996:85 - 88.[9]Higgins A, Bahler L, Porter J. Speaker verification using randomized phrase prompting[J].Digital Signal Processing.1991,1(2):89-[10]Reynolds D A. Comparison of background normalization methods for text-independent speaker verification. In Proc.EUROSPEECH97, Rhodes, Greece, 1997:963 - 966.[11]Reynolds D, Rose R. Robust text-independent speaker identification using Gaussian mixture speaker models[J].IEEE Trans. on Speech Audio Processing.1995, 3(1):72-[12]Martin A.[J].et al.. The DET curve in assessment of detection task performance. In Proc. EUROSPEECH97, Rhodos, Greece.1997,:-
  • 加載中
計量
  • 文章訪問數(shù):  2503
  • HTML全文瀏覽量:  93
  • PDF下載量:  886
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  2004-02-23
  • 修回日期:  2004-07-05
  • 刊出日期:  2005-07-19

目錄

    /

    返回文章
    返回