Instance Based Sparse Classifier Fusion for Speaker Verification
Journal Title: Journal of Information Systems and Telecommunication - Year 2016, Vol 4, Issue 3
Abstract
This paper focuses on the problem of ensemble classification for text-independent speaker verification. Ensemble classification is an efficient method to improve the performance of the classification system. This method gains the advantage of a set of expert classifiers. A speaker verification system gets an input utterance and an identity claim, then verifies the claim in terms of a matching score. This score determines the resemblance of the input utterance and pre-enrolled target speakers. Since there is a variety of information in a speech signal, state-of-the-art speaker verification systems use a set of complementary classifiers to provide a reliable decision about the verification. Such a system receives some scores as input and takes a binary decision: accept or reject the claimed identity. Most of the recent studies on the classifier fusion for speaker verification used a weighted linear combination of the base classifiers. The corresponding weights are estimated using logistic regression. Additional researches have been performed on ensemble classification by adding different regularization terms to the logistic regression formulae. However, there are missing points in this type of ensemble classification, which are the correlation of the base classifiers and the superiority of some base classifiers for each test instance. We address both problems, by an instance based classifier ensemble selection and weight determination method. Our extensive studies on NIST 2004 speaker recognition evaluation (SRE) corpus in terms of EER, minDCF and minCLLR show the effectiveness of the proposed method.
Authors and Affiliations
Mohammad Hasheminejad, Hassan Farsi
Keywords
Related Articles
- EP ID EP184067
- DOI 10.7508/jist.2016.03.007
- Views 112
- Downloads 0
A Fast and Accurate Sound Source Localization Method using Optimal Combination of SRP and TDOA Methodologies
This paper presents an automatic sound source localization approach based on combination of the basic time delay estimation sub method namely, Time Difference of Arrival (TDOA), and Steered Response Power (SRP) methods....
A Global-Local Noise Removal Approach to Remove High Density Impulse Noise
Impulse noise removal from images is one of the most important concerns in digital image processing. Noise must be removed in a way that the main and important information of image is kept. Traditionally, the median filt...
A Hybrid Cuckoo Search for Direct Blockmodeling
As a way of simplifying, size reducing and making sense of the structure of each social network, blockmodeling consists of two major, essential components: partitioning of actors to equivalence classes, called positions,...
A New Cooperative Approach for Cognitive Radio Networks with Correlated Wireless Channels
An effective cooperative cognitive radio system is proposed, when the wireless channels are highly correlated. The system model consists of two multi-antenna secondary users (SU TX and SU RX), constituting the desired li...
Selecting Enterprise Resource Planning System Using Fuzzy Analytic Hierarchy Process Approach
To select an enterprise resource planning (ERP) system is time consuming due to the resource constraints, the software complexity, and the different of alternatives. A comprehensively systematic selection policy for ERP...