APSIPA Transactions on Signal and Information Processing > Vol 5 > Issue 1

Ensemble based speaker recognition using unsupervised data selection

Chien-Lin Huang, National Central University, Republic of China, chiccocl@gmail.com , Jia-Ching Wang, National Central University, Republic of China, Bin Ma, Institute for Infocomm Research (I2R), Singapore
 
Suggested Citation
Chien-Lin Huang, Jia-Ching Wang and Bin Ma (2016), "Ensemble based speaker recognition using unsupervised data selection", APSIPA Transactions on Signal and Information Processing: Vol. 5: No. 1, e10. http://dx.doi.org/10.1017/ATSIP.2016.10

Publication Date: 10 May 2016
© 2016 Chien-Lin Huang, Jia-Ching Wang and Bin Ma
 
Subjects
 
Keywords
Speaker recognitionEnsemble classifierUnsupervised data selection
 

Share

Open Access

This is published under the terms of the Creative Commons Attribution licence.

Downloaded: 712 times

In this article:
I. INTRODUCTION 
II. FEATURE EXTRACTION 
III. DISTANCE METRIC 
IV. CLUSTERING FOR ENSEMBLE BASED SPEAKER RECOGNITION SYSTEMS 
V. EXPERIMENT PROTOCOL 
VI. RESULTS AND ANALYSIS 
VII. CONCLUSION 

Abstract

This paper presents an ensemble-based speaker recognition using unsupervised data selection. Ensemble learning is a type of machine learning that applies a combination of several weak learners to achieve an improved performance than a single learner. A speech utterance is divided into several subsets based on its acoustic characteristics using unsupervised data selection methods. The ensemble classifiers are then trained with these non-overlapping subsets of speech data to improve the recognition accuracy. This new approach has two advantages. First, without any auxiliary information, we use ensemble classifiers based on unsupervised data selection to make use of different acoustic characteristics of speech data. Second, in ensemble classifiers, we apply the divide-and-conquer strategy to avoid a local optimization in the training of a single classifier. Our experiments on the 2010 and 2008 NIST Speaker Recognition Evaluation datasets show that using ensemble classifiers yields a significant performance gain.

DOI:10.1017/ATSIP.2016.10