摘要
针对训练和测试阶段中的语音数据类型(普通话和四川方言)的不匹配导致说话人确认系统性能下降很大的问题,提出了一种新的建立高斯混合模型(GMM)方法——普通话和四川方言按比例混合建立普通话和四川方言联合GMM的方法,并发现使系统针对普通话和四川方言不匹配导致的性能下降率至很低(2.79%)的比例。实验结果表明,该方法可以有效地加强测试阶段针对语种变化的鲁棒性,可以有效的减少普通话和四川方言在训练和测试阶段的不匹配造成的性能下降率。
Due to the mismatch between mandarin and Sichuan dialect in training and test stages, the performance of speaker verification system degrades dramatically. To solve this problem, a combined Gaussian Mixture Model ( GMM), which is trained by proportional pooling mandarin and Sichuan dialect, was presented in this paper, Compared with, the Gaussian mixture model trained solely using mandarin/Sichuan dialect, the combined Gaussian mixture model described the characteristic of speaker from both mandarin and Sichuan dialect. Experiments on a self-built mandarin-Sichuan dialect speech database demonstrate that the introduced combined Gaussian mixture model is more robust for speech mismatching between mandarin and Sichuan dialect. A proper proportion between pooling mandarin and Sichuan dialect speech was also provided.
出处
《计算机应用》
CSCD
北大核心
2008年第3期792-794,共3页
journal of Computer Applications
关键词
说话人确认
高斯混合模型
独立文本
双语种说话人确认
speaker verification
Gaussian Mixture Models (GMM)
text-independent
bilingual speaker verification