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

Abstract

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 estimates. This paper shows that GMM can be easily integrated… (More)
DOI: 10.1109/ICASSP.2015.7178779

Topics

6 Figures and Tables

Cite this paper

@article{Tske2015IntegratingGM, title={Integrating Gaussian mixtures into deep neural networks: Softmax layer with hidden variables}, author={Zolt{\'a}n T{\"{u}ske and Muhammad Ali Tahir and Ralf Schl{\"{u}ter and Hermann Ney}, journal={2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year={2015}, pages={4285-4289} }