In this paper, we improve a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems, ...
In this paper, we improve a recently-proposed uncertainty decod- ing scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems, which ...
It is shown that the recognition accuracy of the DNN-HMM hybrid system improves by incorporating uncertainty decoding and that the proposed weighted ...
In [23] , an approach designed to improve the averaging based MC method is proposed by drawing fewer samples and weighting each DNN's output by a weight that is ...
An improved uncertainty decoding scheme with weighted samples for multi-channel DNN-HMM hybrid systems · DNN Uncertainty Propagation Using GMM-Derived ...
In this paper, we focus on uncertainty decoding based on random sampling, as it has been shown to be promising for improving the accuracy of DNN-based ASR ...
In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems. General ...
We propose a new strategy for generating feature samples from multichannel signals, based on modeling the spatial coherence estimates between different ...
In this article, we propose an uncertainty decoding scheme for DNN-HMM hybrid systems based on numerical sampling. A finite set of samples is drawn from the ...
Missing: weighted | Show results with:weighted
In this paper, we advance a recently-proposed uncertainty decoding scheme for DNN-HMM (deep neural network - hidden Markov model) hybrid systems.