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

Content Provider	IET Digital Library
Author	Wang, Wenchao Xu, Ji Yan, Yonghong
Abstract	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 ivector/ PLDA and some other advanced methods.
Starting Page	357
Ending Page	363
Page Count	7
ISSN	10224653
Volume Number	28
e-ISSN	20755597
Issue Number	Issue 2, Mar (2019)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/cje/28/2
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/cje.2018.06.005
Journal	Chinese Journal of Electronics
Publisher Date	2019-03-01
Access Restriction	Open
Rights Holder	© Chinese Institute of Electronics
Subject Keyword	Algebra Equal Error Rate Identity Vector Extraction Ivector-PLDA Linear Discriminant Analysis Minimum Detection Cost Function National Institute of Standards And Technology Speaker Recognition Evaluation 2010 NIST SRE 2010 Probability Shared Intrinsic Factor Shared Mixture Short-time Speaker Recognition Short-time Utterances SM-PLDA Speaker Identification Information Speaker Recognition Speaker Recognition Evaluation 2010 Extended Task Speaker Recognition System Speech Processing Technique Speech Recognition And Synthesis Standard Probabilistic Linear Discriminant Analysis Method Statistics Vector
Content Type	Text
Resource Type	Article
Subject	Applied Mathematics Electrical and Electronic Engineering

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Probabilistic linear discriminant analysis of i-vector posterior distributions

Relevance vector machines with empirical likelihood-ratio kernels for PLDA speaker verification

The HKCUPU system for the NIST 2010 speaker recognition evaluation

Towards noise-robust speaker recognition using probabilistic linear discriminant analysis

Recent progress in prosodic speaker verification

An efficient implementation of Probabilistic Linear Discriminant Analysis

Phonetically-constrained PLDA modeling for text-dependent speaker verification with multiple short utterances

PLDA for speaker verification with utterances of arbitrary duration

An iterative framework for unsupervised learning in the PLDA based speaker verification

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

Similar Documents

Probabilistic linear discriminant analysis of i-vector posterior distributions

Relevance vector machines with empirical likelihood-ratio kernels for PLDA speaker verification

The HKCUPU system for the NIST 2010 speaker recognition evaluation

Towards noise-robust speaker recognition using probabilistic linear discriminant analysis

Recent progress in prosodic speaker verification

An efficient implementation of Probabilistic Linear Discriminant Analysis

Phonetically-constrained PLDA modeling for text-dependent speaker verification with multiple short utterances

PLDA for speaker verification with utterances of arbitrary duration

An iterative framework for unsupervised learning in the PLDA based speaker verification

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