ARTICULATORY-FEATLRE BASED SEQUENCE KERNEL FOR HIGH-LEVEL SPEAKER VERIFICATION

摘要：

Research has shown that articulatory feature-based phonetic-class pronunciation models (AFCPMs) can capture the pronunciation characteristics of speakers. However, the scoring method used in AFCPMs does not explicitly use the discriminative information available in the training data. To harness this information, this paper proposes converting speaker models to supervectors by stacking the discrete densities in AFCPMs. An AF-kernel is constructed from the supervectors of target speakers, background speakers, and claimants. An AF-kernel based SVM is then trained to classify the super-vectors. Results show that AR-kemel scoring is complementary to likelihood-ratio scoring, leading to better performance when the two scoring methods are combined.

关键词： Speaker verification kernels articulatory features pronunciation models SVM

作者: Shi-Xiong Zhang Man-Wai Mak

作者单位: Dept.of Electronic and Information Engineering, The Hong Kong Polytechnic University

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 2799-2804

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）