Regularized Subspace Gaussian Mixture Models for Speech Recognition
Liang Lu, Arnab Kumar Ghoshal, Steve J. Renals · IEEE Signal Processing Letters · 2011
Subspace Gaussian mixture models (SGMMs) provide a compact representation of the Gaussian parameters in an acoustic model, but may still suffer from over-fitting with insufficient training data. In this letter, the SGMM state parameters are estimated using a penalized maximum-likelihood objective, based on l1and l2regularization, as well as their combination, referred to as the elastic net, for robust model estimation. Experiments on the 5000-word Wall Street Journal transcription task show word error rate reduction and improved model robustness with regularization.