13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Age Estimation from Telephone Speech using i-Vectors

Mohamad Hasan Bahari (1), Mitchell McLaren (2), Hugo Van hamme (1), David van Leeuwen (2)

(1) Center for processing speech and images, KU Leuven, Belgium
(2) Center for Language and Speech Technology, Radboud University Nijmegen, The Netherlands

Motivated by the success of i-vectors in the field of speaker recognition, this paper proposes a new approach for age estimation from telephone speech patterns based on i-vectors. In this method, each utterance is modeled by its corresponding ivector. Then, Support Vector Regression (SVR) is applied to estimate the age of speakers. The proposed method is trained and tested on telephone conversations of the National Institute for Standard in Technology (NIST) 2010 and 2008 Speaker Recognition Evaluations databases. Evaluation results show that the proposed method outperforms different conventional methods in speaker age estimation.

Index Terms: speaker age estimation, i-vector, support vector regression

Full Paper

Bibliographic reference.  Bahari, Mohamad Hasan / McLaren, Mitchell / Van hamme, Hugo / Leeuwen, David van (2012): "Age estimation from telephone speech using i-vectors", In INTERSPEECH-2012, 506-509.