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

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 la...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2011-10, Vol.18 (10), p.563-566
Main Authors: Remes, U., Palomaki, K. J., Raiko, T., Honkela, A., Kurimo, M.
Format: Article
Language:English
Subjects:
Hidden Markov models
Mathematical model
Missing data
Noise measurement
noise robustness
Signal to noise ratio
Speech
Speech recognition
state space methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2011.2163508