Language:

Improving the Effectiveness of Speaker Verification Domain Adaptation With Inadequate In-Domain Data

Digital Resources/Online E-Resources

Title:
Improving the Effectiveness of Speaker Verification Domain Adaptation With Inadequate In-Domain Data
Author: Borgstrom, Bengt J ; Singer,Elliot ; Reynolds,Douglas A ; Sadjadi,Omid
Subjects: Bayesian adaptation ; bayesian networks ; coefficients ; covariance ; digital data ; discriminant analysis ; gaussian distributions ; optimization ; random variables ; speaker verification ; speech ; Statistics and Probability ; uncertainty ; unsupervised domain adaptation
Description: This paper addresses speaker verification domain adaptation with inadequate in-domain data. Specifically, we explore the cases where in-domain data sets do not include speaker labels, contain speakers with few samples, or contain speakers with low channel diversity. Existing domain adaptation methods are reviewed, and their shortcomings are discussed. We derive an unsupervised version of fully Bayesian adaptation which reduces the reliance on rich in-domain data. When applied to domain adaptation with inadequate in-domain data, the proposed approach yields competitive results when the samples per speaker are reduced, and outperforms existing supervised methods when the channel diversity is low, even without requiring speaker labels. These results are validated on the SRE16, which uses a highly inadequate in-domain data set.
Creation Date: 2017
Language: English
Source: DTIC Technical Reports

Back to results list

Previous Result 8 Next Go to Next page


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

Searching Remote Databases, Please Wait