ZHANG Xiang, XIAO Xiang, WANG Haipeng, et al., “Multi-Class Maximum A Posteriori LinearRegression for Speaker Verification,” Chinese Journal of Electronics, vol. 19, no. 4, pp. 641-645, 2010,
Citation: ZHANG Xiang, XIAO Xiang, WANG Haipeng, et al., “Multi-Class Maximum A Posteriori LinearRegression for Speaker Verification,” Chinese Journal of Electronics, vol. 19, no. 4, pp. 641-645, 2010,

Multi-Class Maximum A Posteriori LinearRegression for Speaker Verification

  • Received Date: 2009-11-01
  • Rev Recd Date: 2010-04-01
  • Publish Date: 2010-11-25
  • Maximum likelihood linear regression(MLLR) transforms have proven useful for textindependentspeaker recognition systems. These systemsuse the parameters of MLLR transforms as features forSVM modeling and classification. In this paper, we focuson calculating affine transforms based on a GMMUniversalbackground model (UBM). Rather than estimating transformsusing maximum likelihood criterion, we propose touse Maximum a posteriori linear regression (MAPLR) forfeature extraction. This work is enriched by a multi-classtechnique, which clusters the Gaussian mixtures into regressionclasses and estimates a different transform foreach class. The transforms of all classes are concatenatedinto a supervector for SVM classification. Besides, a furtheraccuracy boost is obtained by combining supervectorsderived from both female and male UBMs into a largersupervector. Experiments on a NIST 2008 SRE corpusshow that the MAPLR system outperforms MLLR andthe multi-class approaches can also bring significant gains.
  • loading
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (840) PDF downloads(913) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return