Dynamic estimation of a noise over estimation factor for Jacobian-based adaptation

Christophe Cerisara (1) , Jean-Claude Junqua (2) , Luca Rigazio (2)

1 PAROLE - Analysis, perception and recognition of speech
2 PSTL - Panasonic Speech Technology Laboratory

In this paper we propose an enhancement of the Jacobian adaptation by estimating automatically a noise over estimation factor which yields to a closer approximation of Parallel model combination (PMC) than the traditional Jacobian adaptation. Noise over estimation factors are estimated at run-time for a set of clustered Gaussians obtained on the training set. Experiments conducted on a French natural number database show that similar performance as PMC can be obtained at the expense of a slight increase in computational complexity as compared to Jacobian adaptation.

Mots clés: jacobian adaptation; reconnaissance automatique de la parole; automatic speech recognition; robustness; robustesse; adaptation jacobienne

Domaines: Autre [cs.OH]

Christophe Cerisara, Jean-Claude Junqua, Luca Rigazio. Dynamic estimation of a noise over estimation factor for Jacobian-based adaptation. IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2002, 2002, Orlando, Florida, 4 p. ⟨inria-00107578⟩