Robust automatic speech recognition with missing and unreliable acoustic data
Speech Communication
Hi-index | 0.00 |
This paper proposes a Vector Autoregressive (VAR) model as a new technique for missing feature reconstruction in ASR. We model the spectral features using multiple VAR models. A VAR model predicts missing features as a linear function of a block of feature frames. We also propose two schemes for VAR training and testing. The experiments on AURORA-2 database have validated the modeling methodology and shown that the proposed schemes are especially effective for low SNR speech signals. The best setting has achieved a recognition accuracy of 88.2% at -5dB SNR on subway noise task when oracle data mask is used.