Lanzhou University of Technology Institutional Repository (LUT_IR)
Research on x-vector speaker recognition algorithm based on Kaldi | |
Zhao, Hong1; Yue, Lupeng1; Wang, Weijie1; Zeng, Xiangyan2 | |
2022 | |
发表期刊 | INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS |
ISSN | 1752-5055 |
卷号 | 15期号:3页码:199-212 |
摘要 | This paper presents a convolutional neural network with an attention mechanism for analysing the spectrogram in an x-vector based speaker recognition system. First, the convolutional neural network (CNN) is used to extract the features of the spectrogram. Then, an attention mechanism is designed to calculate the frame weight in the statistical pooling layer. Finally, probability linear discriminant analysis (PLDA) is used as a back end classifier. The system is implemented using Kaldi speech recognition tools and tests on the Voxceleb1 database. The experimental results show that the combination of spectrogram and CNN gains a relative improvement of 6.7% in equal error rate (EER) compared with the x-vector baseline system. The attention mechanism for the statistical layer further leads to a relative improvement of 26.1%. Overall the proposed method outperforms state-of-the-art methods on the Voxceleb1 database. |
关键词 | spectrogram attention mechanism x-vector speaker recognition Kaldi |
DOI | 10.1504/IJCSM.2022.124725 |
收录类别 | ESCI ; EI |
语种 | 英语 |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Multidisciplinary |
WOS记录号 | WOS:000837752800001 |
出版者 | INDERSCIENCE ENTERPRISES LTD |
EI入藏号 | 20223512671139 |
EI主题词 | Vectors |
EI分类号 | 716.1 Information Theory and Signal Processing ; 741.3 Optical Devices and Systems ; 751.5 Speech ; 903.1 Information Sources and Analysis ; 921.1 Algebra ; 922 Statistical Methods |
来源库 | WOS |
引用统计 | 无
|
文献类型 | 期刊论文 |
条目标识符 | https://ir.lut.edu.cn/handle/2XXMBERH/159869 |
专题 | 兰州理工大学 |
通讯作者 | Yue, Lupeng |
作者单位 | 1.Lanzhou Univ Technol, Sch Comp Sci, Lanzhou 730050, Gansu, Peoples R China; 2.Ft Valley State Univ, Dept Math & Comp Sci, Ft Valley, GA 31030 USA |
第一作者单位 | 兰州理工大学 |
通讯作者单位 | 兰州理工大学 |
第一作者的第一单位 | 兰州理工大学 |
推荐引用方式 GB/T 7714 | Zhao, Hong,Yue, Lupeng,Wang, Weijie,et al. Research on x-vector speaker recognition algorithm based on Kaldi[J]. INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS,2022,15(3):199-212. |
APA | Zhao, Hong,Yue, Lupeng,Wang, Weijie,&Zeng, Xiangyan.(2022).Research on x-vector speaker recognition algorithm based on Kaldi.INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS,15(3),199-212. |
MLA | Zhao, Hong,et al."Research on x-vector speaker recognition algorithm based on Kaldi".INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS 15.3(2022):199-212. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论