Missing data recognition has been proposed to increase noise robustness of automatic speech recognition. This strategy relies on the use of a spectrographic mask that gives information about the true clean speech energy of a corrupted signal. This information is then used to refine the data process during the decoding step. We propose in this work a new mask that provides more information about the clean speech contribution than classical masks based on a Signal to Noise Ratio (SNR) thresholding. The proposed mask is described and compared to another missing data approach based on SNR thresholding. Experimental results show a significant word error rate reduction induced by the proposed approach. Moreover, the proposed mask outperforms the ETSI advanced front-end on the HIWIRE corpus.
Bibliographic reference. Demange, Sébastien / Cerisara, Christophe / Haton, Jean-Paul (2007): "Accurate marginalization range for missing data recognition", In INTERSPEECH-2007, 914-917.