English

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.

Keywords

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}
}
R2 v1 2026-06-22T20:02:42.212Z