Feature Selection and Model Optimization for Semi-supervised Speaker Spotting

Chetupalli, Srikanth Raj and Gopalakrishnan, Anand and Sreenivas, Thippur V (2016) Feature Selection and Model Optimization for Semi-supervised Speaker Spotting. In: 24th European Signal Processing Conference (EUSIPCO), AUG 28-SEP 02, 2016, Budapest, HUNGARY, pp. 135-139.

PDF 24th_Eur_Sig_Pro_Con_135_2016.pdf - Published Version Restricted to Registered users only Download (350kB) | Request a copy

Abstract

We explore, experimentally, feature selection and optimization of stochastic model parameters for the problem of speaker spotting. Based on an initially identified segment of speech of a speaker, an iterative model refinement method is developed along with a latent variable mixture model so that segments of the same speaker are identified in a long speech record. It is found that a GMM with moderate number of mixtures is better suited for the task than a large number mixture model as used in speaker identification. Similarly, a PCA based low-dimensional projection of MFCC based feature vector provides better performance. We show that about 6 seconds of initially identified speaker data is sufficient to achieve > 90 % performance of speaker segment identification.

Item Type:	Conference Proceedings
Series.:	European Signal Processing Conference
Additional Information:	Copy right for this article belongs to the IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	17 Feb 2017 09:23
Last Modified:	17 Feb 2017 09:23
URI:	http://eprints.iisc.ac.in/id/eprint/56264

Actions (login required)

View Item