Muhammad Ali Tahir — accepted AI-conference papers

2015

Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables

Zoltán Tüske, Muhammad Ali Tahir, Ralf Schlüter, Hermann Ney

ICASSP 2015accepted

In the hybrid approach, neural network output directly serves as hidden Markov model (HMM) state posterior probability estimates. In contrast to this, in the tandem approach neural network output is used as input features to improve classic Gaussian mixture model (GMM) based emission probability est…

Cited by 45 Source ↗Scholar ↗

2015

Investigation of mixture splitting concept for training linear bottlenecks of deep neural network acoustic models

Muhammad Ali Tahir, Simon Wiesler, Ralf Schlüter, Hermann Ney

ICASSP 2015accepted

A Gaussian or log-linear mixture model trained by maximum likelihood may be trained further using discriminative training. It is desirable that the mixture splitting is also done during the discriminative training, to achieve better mixture density distribution. In previous work such a discriminativ…

Cited by 0 Source ↗Scholar ↗