Abstract

We propose a simplified and supervised i-vector modeling scheme for the speaker age regression task. The supervised i-vector is obtained by concatenating the label vector and the linear regression matrix at the end of the mean super-vector and the i-vector factor loading matrix, respectively. Different label vector designs are proposed to increase the robustness of the supervised i-vector models. Finally, Support Vector Regression (SVR) is deployed to estimate the age of the speakers. The proposed method outperforms the conventional i-vector baseline for speaker age estimation. A relative 2.4% decrease in Mean Absolute Error and 3.33% increase in correlation coefficient is achieved using supervised i-vector modeling using different label designs on the NIST SRE 2008 dataset male part.

Date

2014

Authors

Prashanth Gurunath Shivakumar, Ming Li, Vedant Dhandhania, Shrikanth S Narayanan

Conference

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Pages

4833-4837

Publisher

IEEE