首页|Identity Vector Extraction Using Shared Mixture of PLDA for Short-Time Speaker Recognition

Identity Vector Extraction Using Shared Mixture of PLDA for Short-Time Speaker Recognition

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
The state-of-the-art speaker recognition system degrades performance rapidly dealing with short-time utterances. It is known to all that identity vectors (i-vectors) extracted from short utterances have large uncertainties and standard Probabilistic linear discriminant analysis (PLDA) method can not exploit this uncertainty to reduce the effect of duration variation. In this work, we use Shared mixture of PLDA (SM-PLDA) to remodel the i-vectors utilizing their uncertainties. SM-PLDA is an improved generative model with a shared intrinsic factor, and this factor can be regarded as an identity vector containing speaker indentification information. This identity vector can be modeled by PLDA. Experimental results are evaluated by both equal error rate and minimum detection cost function. The results conducted on the National institute of standards and technology (NIST) Speaker recognition evaluation (SRE) 2010 extended tasks show that the proposed method has achieved significant improvements compared with i-vector/PLDA and some other advanced methods.

Short-time utteranceSpeaker recogni-tionShared mixture of PLDAIdentity vector

WANG Wenchao、XU Ji、YAN Yonghong

展开 >

Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China

University of Chinese Academy of Sciences, Beijing 100049, China

Xinjiang Laboratory of Minority Speech and Language Information Processing, Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Urumchi 830011, China

This work is partially supported by the National Natural Science Foundation of ChinaThis work is partially supported by the National Natural Science Foundation of ChinaThis work is partially supported by the National Natural Science Foundation of ChinaThis work is partially supported by the National Natural Science Foundation of ChinaNational Key Research and Development PlanNational Key Research and Development PlanKey Science and Technology Project of the Xinjiang Uygur Autonomous RegionPre-research Project for Equipment of General Information System

11590770-4No.U1536117No.11504406No.114611410042016YFB0801203No.2016YFB08012002016A03007-1JZX2017-0994/Y306

2019

10.1049/cje.2018.06.005

中国电子杂志(英文版)

中国电子杂志(英文版)

CSTPCDCSCDSCIEI
ISSN：1022-4653
年,卷(期)：2019.28(2)
  • 1
  • 20