Speaker age estimation and gender detection based on supervised Non-Negative Matrix Factorization

Author

Bahari, Mohamad Hasan ; Van hamme, Hugo

Author_Institution

Centre for Process. Speech & Images, Katholieke Univ. Leuven, Leuven, Belgium

fYear

2011

fDate

28-28 Sept. 2011

Firstpage

1

Lastpage

6

Abstract

In many criminal cases, evidence might be in the form of telephone conversations or tape recordings. Therefore, law enforcement agencies have been concerned about accurate methods to profile different characteristics of a speaker from recorded voice patterns, which facilitate the identification of a criminal. This paper proposes a new approach for speaker gender detection and age estimation, based on a hybrid architecture of Weighted Supervised Non-Negative Matrix Factorization (WSNMF) and General Regression Neural Network (GRNN). Evaluation results on a corpus of read and spontaneous speech in Dutch confirms the effectiveness of the proposed scheme.

Keywords

criminal law; gender issues; matrix decomposition; neural nets; regression analysis; speaker recognition; gender detection; general regression neural network; hybrid architecture; law enforcement agency; recorded voice pattern; speaker age estimation; tape recording; telephone conversation; weighted supervised nonnegative matrix factorization; Accuracy; Acoustics; Estimation; Speech; Training; Training data; Wireless sensor networks; age estimation; gender detection; general regression neural network; weighted supervised non-negative matrix factorization;

fLanguage

English

Publisher

ieee

Conference_Titel

Biometric Measurements and Systems for Security and Medical Applications (BIOMS), 2011 IEEE Workshop on

Conference_Location

Milan

Print_ISBN

978-1-4577-0765-0

Type

conf

DOI

10.1109/BIOMS.2011.6052385

Filename

6052385