Missing-Feature Reconstruction With a Bounded Nonlinear State-Space Model

Ulpu Remes, Kalle J. Palomäki, Tapani Raiko, Antti Honkela, Mikko Kurimo

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.