DNN-based uncertainty estimation for weighted DNN-HMM ASR
Sound
2017-05-31 v1 Neural and Evolutionary Computing
Abstract
In this paper, the uncertainty is defined as the mean square error between a given enhanced noisy observation vector and the corresponding clean one. Then, a DNN is trained by using enhanced noisy observation vectors as input and the uncertainty as output with a training database. In testing, the DNN receives an enhanced noisy observation vector and delivers the estimated uncertainty. This uncertainty in employed in combination with a weighted DNN-HMM based speech recognition system and compared with an existing estimation of the noise cancelling uncertainty variance based on an additive noise model. Experiments were carried out with Aurora-4 task. Results with clean, multi-noise and multi-condition training are presented.
Cite
@article{arxiv.1705.10368,
title = {DNN-based uncertainty estimation for weighted DNN-HMM ASR},
author = {José Novoa and Josué Fredes and Néstor Becerra Yoma},
journal= {arXiv preprint arXiv:1705.10368},
year = {2017}
}