Automatic Speech Recognition System with Output-Gate Projected Gated Recurrent Unit

Gaofeng CHENG  Pengyuan ZHANG  Ji XU  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.2   pp.355-363
Publication Date: 2019/02/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDP7155
Type of Manuscript: PAPER
Category: Speech and Hearing
Keyword: 
GRU,  LSTM,  neural network language model,  speech recognition,  

Full Text: PDF(747.8KB)
>>Buy this Article


Summary: 
The long short-term memory recurrent neural network (LSTM) has achieved tremendous success for automatic speech recognition (ASR). However, the complicated gating mechanism of LSTM introduces a massive computational cost and limits the application of LSTM in some scenarios. In this paper, we describe our work on accelerating the decoding speed and improving the decoding accuracy. First, we propose an architecture, which is called Projected Gated Recurrent Unit (PGRU), for ASR tasks, and show that the PGRU can consistently outperform the standard GRU. Second, to improve the PGRU generalization, particularly on large-scale ASR tasks, we propose the Output-gate PGRU (OPGRU). In addition, the time delay neural network (TDNN) and normalization methods are found beneficial for OPGRU. In this paper, we apply the OPGRU for both the acoustic model and recurrent neural network language model (RNN-LM). Finally, we evaluate the PGRU on the total Eval2000 / RT03 test sets, and the proposed OPGRU single ASR system achieves 0.9% / 0.9% absolute (8.2% / 8.6% relative) reduction in word error rate (WER) compared to our previous best LSTM single ASR system. Furthermore, the OPGRU ASR system achieves significant speed-up on both acoustic model and language model rescoring.