Incorporating mask modelling for noise-robust automatic speech recognition


In this paper we investigate an incorporation of mask modelling into an HMM-based ASR system. The mask model is estimated for each HMM state and mixture by using a separate Viterbi-style training procedure and it expresses which regions of the spectrum are expected to be uncorrupted by noise for the HMM state. Experimental evaluation is performed on noisy… (More)
DOI: 10.1109/ICASSP.2009.4960487

5 Figures and Tables


  • Presentations referencing similar topics