Knowledge Commons of Institute of Automation,CAS
Centroid-aware local discriminative metric learning in speaker verification | |
Sheng, Kekai1,2; Dong, Weiming1; Li, Wei3; Razik, Joseph4; Huang, Feiyue3; Hu, Baogang1 | |
发表期刊 | PATTERN RECOGNITION |
2017-12-01 | |
卷号 | 72期号:72页码:176-185 |
文章类型 | Article |
摘要 | We propose a new mechanism to pave the way for efficient learning against class-imbalance and improve representation of identity vector (i-vector) in automatic speaker verification (ASV). The insight is to effectively exploit the inherent structure within ASV corpus - centroid priori. In particular: (1) to ensure learning efficiency against class-imbalance, the centroid-aware balanced boosting sampling is proposed to collect balanced mini-batch; (2) to strengthen local discriminative modeling on the mini-batches, neighborhood component analysis (NCA) and magnet loss (MNL) are adopted in ASV-specific modifications. The integration creates adaptive NCA (AdaNCA) and linear MNL (LMNL). Numerical results show that LMNL is a competitive candidate for low-dimensional projection on i-vector (EER=3.84% on SRE2008, EER=1.81% on SRE2010), enjoying competitive edge over linear discriminant analysis (LDA). AdaNCA (EER=4.03% on SRE2008, EER=2.05% on SRE2010) also performs well. Furthermore, to facilitate the future study on boosting sampling, connections between boosting sampling, hinge loss and data augmentation have been established, which help understand the behavior of boosting sampling further. (C) 2017 Elsevier Ltd. All rights reserved. |
关键词 | Text-independent Asv Centroid-aware Balanced Boosting Sampling Adaptive Neighborhood Component Analysis Linear Magnet |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1016/j.patcog.2017.07.007 |
关键词[WOS] | RECOGNITION ; CLASSIFICATION ; SPEECH ; END |
收录类别 | SCI |
语种 | 英语 |
项目资助者 | National Natural Science Foundation of China (NSFC)(61573348 ; Institute of Automation Chinese Academy of Sciences (CASIA)-Tencent Youtu Joint Research Project ; 61620106003 ; 61672520) |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000411545400013 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/19533 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
作者单位 | 1.Chinese Acad Sci, Inst Automat, LIAMA NLPR, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Tencent Inc, Lab Youtu, Shanghai, Peoples R China 4.Univ Toulon & Var, Lab LSIS, Toulon, France |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Sheng, Kekai,Dong, Weiming,Li, Wei,et al. Centroid-aware local discriminative metric learning in speaker verification[J]. PATTERN RECOGNITION,2017,72(72):176-185. |
APA | Sheng, Kekai,Dong, Weiming,Li, Wei,Razik, Joseph,Huang, Feiyue,&Hu, Baogang.(2017).Centroid-aware local discriminative metric learning in speaker verification.PATTERN RECOGNITION,72(72),176-185. |
MLA | Sheng, Kekai,et al."Centroid-aware local discriminative metric learning in speaker verification".PATTERN RECOGNITION 72.72(2017):176-185. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Centroid-aware local(2013KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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