论文信息 - Missing-Feature Reconstruction With a Bounded Nonlinear State-Space Model

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 large-vocabulary continuous speech recognition task with babble and impulsive noise, using observed bounds in NSSM state estimation significantly improved the method performance.

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

[1] Phil D. Green,et al. Robust automatic speech recognition with missing and unreliable acoustic data , 2001, Speech Commun..

[2] S. Vaseghi. Detection and suppression of impulsive noise in speech communication systems , 1990 .

[3] Mikko Kurimo,et al. Unlimited vocabulary speech recognition with morph language models applied to Finnish , 2006, Comput. Speech Lang..

[4] Richard M. Stern,et al. Reconstruction of missing features for robust speech recognition , 2004, Speech Commun..

[5] Bert Cranen,et al. Sparse imputation for large vocabulary noise robust ASR , 2011, Comput. Speech Lang..

[6] Hugo Van hamme,et al. Compressive Sensing for Missing Data Imputation in Noise Robust Speech Recognition , 2010, IEEE Journal of Selected Topics in Signal Processing.

[7] Juha Karhunen,et al. State Inference in Variational Bayesian Nonlinear State-Space Models , 2006, ICA.

[8] Juha Karhunen,et al. An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models , 2002, Neural Computation.