欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
支持向量机在语种识别技术中获得了广泛的研究和应用，并且达到和传统混合高斯模型相当的性能。高斯超向量．支持向量机系统将高斯混合模型与支持向量机有效地结合起来，采用高斯超向量核函数，以支持向量机作为后端分类器。重点介绍基于高斯超向量一支持向量机的语种识别系统，并和传统的高斯混合模型系统进行比较。在美国国家标准技术研究院2003年和2007年语种识别评测数据集上进行实验。实验结果表明，高斯超向量．支持向量机系统相对于混合高斯模型建模的方法，在长时数据上有较明显的性能优势。
英文摘要：
The Support Vector Machine（SVM） has been widely used in language recognition. It has reached comparable perfor- mance with the traditional Gaussian Mixture Model（GMM）. Gaussian Super Vector-Support Vector Machine （GSV-SVM）, which effectively combines GMM and SVM, is presented in this paper. The experiments are carried out on the NIST LRE2003 and LRE2007 test corpus. The results indicate that the GSV-SVM system can achieve significant improvements on the long-time duration test set, compared with the method of GMM.
同期刊论文项目
同项目期刊论文
Speech Enhancement Using Robust Generalized Side lobe Canceller with Multi-Channel Post-Filtering in
A Novel Similarity Measure to Induce Semantic Classes and Its Application for Language Model Adaptat
Multi-resolution time frequency feature and complementary combination for short utterance speaker re
Acoustic characteristics of stop consontants in fluent reading Chinese Putonghua speech of adult stu
Auditory frequency-following response: a neurophysiological measure for studying the “cocktail-party
Adding irrelevant information to the content prime reduces the prime-induced unmasking effect on spe
Enhancing the Robustness of the Posterior-Based Confidence Measures Using Entropy Information for Sp
Noise Robust Feature Scheme for Automatic Speech Recognition Based on Auditory Perceptual Mechanisms
位置：