Speaker identification by combining multiple classifiers using Dempster-Shafer theory of evidence

Date

2003-11-01

Author

Altincay, H
Demirekler, Mübeccel

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

143
views

0
downloads

This paper presents a multiple classifier approach as an alternative solution to the closed-set text-independent speaker identification problem. The proposed algorithm which is based on Dempster-Shafer theory of evidence computes the first and Rth level ranking statistics. Rth level confusion matrices extracted from these ranking statistics are used to cluster the speakers into model sets where they share set specific properties. Some of these model sets are used to reflect the strengths and weaknesses of the classifiers while some others carry speaker dependent ranking statistics of the corresponding classifier. These information sets from multiple classifiers are combined to arrive at a joint decision. For the combination task, a rule-based algorithm is developed where Dempster's rule of combination is applied in the final step. Experimental results have shown that the proposed method performed much better compared to some other rank-based combination methods.

Subject Keywords

Decision combination, Rule, Models, Speech, Systems, Information, Verification, Classification, Recognition, Data fusion

URI

https://hdl.handle.net/11511/57049

Journal

SPEECH COMMUNICATION

DOI

https://doi.org/10.1016/s0167-6393(03)00032-3

Collections

Graduate School of Natural and Applied Sciences, Article

Suggestions

OpenMETU
Core

Speaker identification through use of features selected using genetic algorithm Haydar, A; Demirekler, Mübeccel; Yurtseven, MK (Institution of Engineering and Technology (IET), 1998-01-08) The authors introduce the use of a genetic algorithm in the reduction of a 24 parameter (12 LPC derived cepstral coefficients +12 Delta-cepstral coefficients) set to a five, six, seven, eight or ten parameter set, for each speaker in text-independent speaker identification. The experimental results show that there is similar to 5% increase in the recognition rate when the reduced set of parameters is used.
Use of model confusion learning for speaker identification a rule-based approach Altincay, H; Demirekler, Mübeccel (1999-06-23) This paper presents a multiple classifier system for text-independent speaker identification (SI). For the speaker identification problem, several different classifiers can be developed, each having strengths and weaknesses compared to the others. When the strengths and weaknesses of the individual classifiers do not overlap, i.e. a speaker which is misclassified by one classifier is correctly classified by some others, robust classification systems can be developed with the use of multiple classifiers. The...
Feature selection using genetics-based algorithm and its application to speaker identification Demirekler, Mübeccel; Haydar, A (1999-03-19) This paper introduces the use of genetics-based algorithm in the reduction of 24 parameter set (i.e the base set) to a 5,6,7,8 or 10 parameter set, for each speaker in text-independent speaker identification. The feature selection is done by finding the best features that discriminates a person from his/her two closest neighbors. The experimental results show that there is approximately 5% increase in the recognition rate when the reduced set of parameters are used. Also the amount of calculation necessary ...
Text summarization using Latent Semantic Analysis Ozsoy, Makbule Gulcin; Alpaslan, Ferda Nur; Çiçekli, İlyas (SAGE Publications, 2011-08-01) Text summarization solves the problem of presenting the information needed by a user in a compact form. There are different approaches to creating well-formed summaries. One of the newest methods is the Latent Semantic Analysis (LSA). In this paper, different LSA-based summarization algorithms are explained, two of which are proposed by the authors of this paper. The algorithms are evaluated on Turkish and English documents, and their performances are compared using their ROUGE scores. One of our algorithms...
Input signal shaping for target identification using genetic algorithms Sayan, Gönül; Leblebicioğlu, Mehmet Kemal (Wiley, 1998-02-01) This paper presents a novel approach for synthesizing an input signal to be used in natural resonance-based target identification. In this problem, both the shape and the duration of an input signal are initially unknown to be determined through an optimization procedure based on genetic algorithms. (C) 1998 John Wiley & Sons, Inc.

Citation Formats

H. Altincay and M. Demirekler, “Speaker identification by combining multiple classifiers using Dempster-Shafer theory of evidence,” SPEECH COMMUNICATION, pp. 531–547, 2003, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/57049.