Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training

Abstract

The use of deep neural networks (DNNs) for feature extraction and Gaussian mixture models (GMMs) for acoustic modelling is often termed a tandem system configuration and can be viewed as a Gaussian mixture density neural network (MDNN). Compared to the direct use of DNN output probabilities in the acoustic model, the tandem approach suffers from a major… (More)
DOI: 10.1109/ICASSP.2017.7953111

Topics

4 Figures and Tables

Cite this paper

@article{Zhang2017JointOO, title={Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training}, author={Chao Zhang and Philip C. Woodland}, journal={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year={2017}, pages={5015-5019} }