The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
Bookmark and Share
The Speaker Recognition System Based on the Dynamic MFCC
Author(s): 
Pages: 596-601
Year: Issue:  5
Journal: Pattern Recognition and Artificial Intelligence

Keyword:  美尔频率倒谱系数(MFCC) 基音检测 说话人识别 高斯混合模型;
Abstract: 提出了一种基于动态MFCC特征的说话人识别算法,该算法根据说话人的基音频率随语境变化的特点,通过动态构建基于说话人基音频率的Mel-滤波器组,以抽取可以表征说话人身份特征的动态MFCC参数,提高说话人辨识的准确性和鲁棒性。此外,本文还讨论了基于高斯混合模型的分类器设计问题,给出了一个通过聚类分析获得高斯混合模型的最优混合度与相关模型参数的初始估计的方法。实验证明,本文所提出的方法在实际中能够获得较好的识别结果。
Related Articles
No related articles found