Conference paper

MARTÍNEZ González David, BURGET Lukáš, STAFYLAKIS Themos, LEI Yun, KENNY Patrick and LLEIDA Eduardo. Unscented Transform For Ivector-based Noisy Speaker Recognition. In: Proceedings of ICASSP 2014. Florencie: IEEE Signal Processing Society, 2014, pp. 4070-4074. ISBN 978-1-4799-2892-7.
Publication language:english
Original title:Unscented Transform For Ivector-based Noisy Speaker Recognition
Title (cs):Unscentovaná transformace pro rozpoznávání řečníka v šumu založené na i-vektorech
Proceedings:Proceedings of ICASSP 2014
Conference:The 39th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Place:Florencie, IT
Publisher:IEEE Signal Processing Society
Noise Robust Speaker Recognition, Unscented Transform, Vector Taylor Series, iVector
This article is about new version of an unscented transform for Ivector-based noisy speaker recognition.
Recently, a new version of the iVector modelling has been proposed for noise robust speaker recognition, where the nonlinear function that relates clean and noisy cepstral coefficients is approximated by a first order vector Taylor series (VTS). In this paper, it is proposed to substitute the first order VTS by an unscented transform, where unlike VTS, the nonlinear function is not applied over the clean model parameters directly, but over a set of sampled points. The resulting points in the transformed space are then used to calculate the model parameters. For very low signal-to-noise ratio improvements in equal error rate of about 7% for a clean backend and of 14.50% for a multistyle backend are obtained.
   author = {David Gonz{\'{a}}lez Mart{\'{i}}nez and
	Luk{\'{a}}{\v{s}} Burget and Themos Stafylakis and
	Yun Lei and Patrick Kenny and Eduardo LLeida},
   title = {Unscented Transform For Ivector-based Noisy
	Speaker Recognition},
   pages = {4070--4074},
   booktitle = {Proceedings of ICASSP 2014},
   year = 2014,
   location = {Florencie, IT},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4799-2892-7},
   doi = {10.1109/ICASSP.2014.6854361},
   language = {english},
   url = {}

Your IPv4 address:
Switch to https