This paper presented our work on applying Recurrent Deep Stacking Networks (RDSNs) to Robust Automatic Speech Recognition (ASR) tasks. In the paper, we also proposed a more efficient yet comparable substitute to RDSN, Bi- Pass Stacking Network (BPSN). The main idea of these two models is to add phoneme-level information into acoustic models, transforming an acoustic model to the combination of an acoustic model and a phoneme-level N-gram model. Experiments showed that RDSN and BPsn can substantially improve the performances over conventional DNNs.
@article{arxiv.1612.04675,
title = {Recurrent Deep Stacking Networks for Speech Recognition},
author = {Peidong Wang and Zhongqiu Wang and Deliang Wang},
journal= {arXiv preprint arXiv:1612.04675},
year = {2020}
}