Language Identification with Score-based Unsupervised Adaptation Method

摘要：

In the text-independent language identification research, the information of previous trials can be adopted to update the language models or the test scores dynamically. This process is defined as the unsupervised mode, which can make a coupling between the trials and the language models. Although the unsupervised mode adaptation is very useful for real language recognition application, the time requirement for both training and testing is consuming process. In this paper, a score-based unsupervised adaptation is proposed as well as modelbased unsupervised adaptation. In the score-based unsupervised adaptation mode, a Gaussian model is introduced as a prior score distribution. Then the MAP method is adopted to adjust the parameters of the score normalization. In the test process, the unsupervised score adaptation can apparently improve the performance of GMM-UBM.

关键词： component Language Identification GMM-UBM MAP Unsupervised Adaptation

作者: Xiuhua Zeng Taoxiang Yang Jian Yang Yonghua Xu

作者单位: College of Physics and Electronic Engineering Qujing Normal University Qujing, China School of Information Science and Engineering Yunnan University, Kunming Yunnan, China

会议类型: 国际会议

会议名称: 2010 International Conference on Circuit and Signal Processing(2010年电路与信号处理国际会议 ICCSP 2010)

会议地点: 上海

会议语种:英文

页码: 68-71

在线出版日期: 2010-12-25（万方平台首次上网日期，不代表论文的发表时间）