13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Phonotactic Language Recognition using iVvectors and Phoneme Posteriogram Counts

Luis Fernando D'Haro (1), Ondřej Glembek (2), Oldřich Plchot (2), Pavel Matějka (2), Mehdi Soufifar (2), Ricardo Cordoba (1), Jan Černocký (2)

(1) Speech Technology Group, Dept. of Electronic Engineering, E.T.S.I. Telecomunicación, Universidad Politécnica de Madrid. Ciudad Universitaria, Madrid, Spain
(2) Brno University of Technology, Speech@FIT group, and IT4I Center of Excellence, Brno, Czech Republic

This paper describes a novel approach to phonotactic LID, where instead of using soft-counts based on phoneme lattices, we use posteriogram to obtain n-gram counts. The high-dimensional vectors of counts are reduced to low-dimensional units for which we adapted the commonly used term i-vectors. The reduction is based on multinomial subspace modeling and is designed to work in the total-variability space. The proposed technique was tested on the NIST 2009 LRE set with better results to a system based on using soft-counts (Cavg on 30s: 3.15% vs 3.43%), and with very good results when fused with an acoustic i-vector LID system (Cavg on 30s acoustic 2.4% vs 1.25%). The proposed technique is also compared with another low dimensional projection system based on PCA. In comparison with the original soft-counts, the proposed technique provides better results, reduces the problems due to sparse counts, and avoids the process of using pruning techniques when creating the lattices.

Index Terms: subspace modeling, multinomial distributions, LID

Full Paper

Bibliographic reference.  D'Haro, Luis Fernando / Glembek, Ondřej / Plchot, Oldřich / Matějka, Pavel / Soufifar, Mehdi / Cordoba, Ricardo / Černocký, Jan (2012): "Phonotactic language recognition using ivvectors and phoneme posteriogram counts", In INTERSPEECH-2012, 42-45.