GMM Based Speaker Recognition on Readily Available Databases

GMM Based Speaker Recognition on Readily Available Databases
复制标题

基于 GMM 的现成数据库上的说话人识别

DOI:
--
复制
发表时间:
2003
期刊:
--
影响因子:
--
通讯作者:
K. Paliwal
K. Paliwal
中科院分区:
--
文献类型:
--
作者:
B. R. Wildermoth;K. Paliwal

文献摘要

参考文献

被引文献

相似文献

- 在本文中,我们给出了最流行的数据库中使用的说话人识别评估的概述,并清楚地概述了使用它们的训练和测试ASR系统的手段。完整的ASR系统,包括特征提取和分类都明确地详细解释。使用TIMIT,YOHO和ANDOSL数据库上的各种形式的MFCC特征,报告了基于GMM的说话人验证和识别系统的性能。
— In this paper we give an overview of the most popular databases used in speaker recognition evaluation and clearly outline the means of training and testing an ASR system using them. The complete ASR system including both feature extraction and classification is explicitly explained in great detail. The performance of a GMM based system for speaker verification and identification is reported using various forms of MFCC features on the TIMIT, YOHO and ANDOSL databases.
DOI: 10.1109/89.365379
发表时间: 1995-01-01
期刊: IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING
影响因子: --
作者:
REYNOLDS, DA;ROSE, RC
通讯作者: ROSE, RC