Title :
Missing-Feature Reconstruction With a Bounded Nonlinear State-Space Model
Author :
Remes, Ulpu ; Palomäki, Kalle J. ; Raiko, Tapani ; Honkela, Antti ; Kurimo, Mikko
Author_Institution :
Sch. of Sci., Adaptive Inf. Res. Centre, Aalto Univ., Espoo, Finland
Abstract :
Missing-feature reconstruction can improve speech recognition performance in unknown noisy environments. In this work, we examine using a nonlinear state-space model (NSSM) for missing-feature reconstruction and propose estimation with observed bounds to improve the NSSM performance. Evaluated in large-vocabulary continuous speech recognition task with babble and impulsive noise, using observed bounds in NSSM state estimation significantly improved the method performance.
Keywords :
signal reconstruction; speech recognition; state estimation; NSSM state estimation; babble noise; bounded nonlinear state-space model; impulsive noise; large-vocabulary continuous speech recognition task; missing-feature reconstruction; speech recognition performance; Hidden Markov models; Mathematical model; Noise measurement; Signal to noise ratio; Speech; Speech recognition; Missing data; noise robustness; speech recognition; state space methods;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2011.2163508
