Joint uncertainty decoding (JUD) is a model-based noise compensation technique for conventional Gaussian Mixture Model (GMM) based speech recognition ...

This paper addresses robust speech recognition based on subspace Gaussian mixture models (SGMMs) using joint uncertainty decoding (JUD) noise compensation.

Joint uncertainty decoding (JUD) is a model-based noise compensation technique for conventional Gaussian Mixture Model (GMM) based speech recognition systems.

This paper applies UT to noise compensation of the subspace Gaussian mixture model (SGMM). Since UT requires relatively smaller number of samples for accurate ...

Abstract: Abstract-Joint uncertainty decoding (JUD) is a model-based noise compensation technique for conventional Gaussian Mixture Model (GMM) based speech ...

The subspace Gaussian mixture model—A structured model for speech recognition. Computer Speech & Language, 25(2):404–439. Liang Lu, Interspeech, September, 2012.

Bibliographic details on Joint Uncertainty Decoding for Noise Robust Subspace Gaussian Mixture Models.

Joint Uncertainty Decoding for Noise Robust Subspace Gaussian Mixture Models · IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), July 2013.

Liang Lu, Arnab Ghoshal, Steve Renals: Joint uncertainty decoding with unscented transform for noise robust subspace Gaussian mixture models.

Joint uncertainty decoding (JUD) is a model-based noise compensation technique for conventional Gaussian Mixture Model (GMM) based speech recognition ...