Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural network based on context-dependent state acoustic model, if the decoder is unchanged. In this paper, we propose a novel frame retaining method which is applied in decoding. The system which combined frame retaining with frame stacking could reduces the time consumption of both training and decoding. Long short-term memory (LSTM) recurrent neural networks (RNNs) using it achieve almost linear training speedup and reduces relative 41\% real time factor (RTF). At the same time, recognition performance is no degradation or improves sightly on Shenma voice search dataset in Mandarin.
@article{arxiv.1705.05992,
title = {Frame Stacking and Retaining for Recurrent Neural Network Acoustic Model},
author = {Xu Tian and Jun Zhang and Zejun Ma and Yi He and Juan Wei},
journal= {arXiv preprint arXiv:1705.05992},
year = {2017}
}