MISSING FEATURE IMPUTATION OF LOG-SPECTRAL DATA FOR NOISE ROBUST ASR

In this paper, we present a missing feature (MF) imputation algorithm for log-spectral data with applications to noise robust ASR. Drawing from previous work [1], we adapt the previously proposed spectrographic reconstruction solution to the liftered log-spectral domain by introducing log-spectral flooring (LS-FLR). LS-FLR is shown to be an efficient and effective noise robust feature extraction technique. When LSFLR is integrated in deriving the novel log-spectral data imputation framework, the overall system is shown to provide significant improvements in noise robust speech recognition.