Speaker Verification Using Sparse Representations on Total Variability i-vectors
Speaker Verification Using Sparse Representations on Total Variability i-vectors
复制标题
DOI：
10.21437/interspeech.2011-149
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Ming Li;Xiang Zhang;Yonghong Yan;Shrikanth S. Narayanan
中科院分区：
文献类型：
--
作者：
Ming Li;Xiang Zhang;Yonghong Yan;Shrikanth S. Narayanan
本文在进行类内协方差归一化和线性判别分析通道补偿后，利用二次约束最小化计算得到的稀疏表示对低维总变异性空间中的i向量进行建模。首先，我们提出了背景归一化残差作为评分准则。其次，我们证明了利用Tnorm数据作为过完备字典中的非目标样本可以有效地实现Tnorm。最后，通过融合传统的基于i向量的支持向量机（SVM）和余弦距离评分系统，我们证明了系统整体性能的提高。实验结果表明，该融合系统在NIST SRE 2008的单-单多语言手持电话任务上，经Tnorm处理后的平均错误率（EER）分别为4.05%（男性）和5.25%（女性），在男性和女性任务上的相对错误率分别降低7.1%和4.9%，优于支持向量机基线。
In this paper, the sparse representation computed by lminimization with quadratic constraints is employed to model the i-vectors in the low dimensional total variability space after performing the Within-Class Covariance Normalization and Linear Discriminate Analysis channel compensation. First, we propose the background normalized l residual as a scoring criterion. Second, we demonstrate that the Tnorm can be efficiently achieved by using the Tnorm data as the non-target samples in the over-complete dictionary. Finally, by fusing with the conventional i-vector based support vector machine (SVM) and cosine distance scoring system, we demonstrate overall system performance improvement. Experimental results show that the proposed fusion system achieved 4.05% (male) and 5.25% (female) equal error rate (EER) after Tnorm on the single-single multi-language handheld telephone task of NIST SRE 2008 and outperformed the SVM baseline by yielding 7.1% and 4.9% relative EER reduction for the male and female tasks, respectively.