The use of future contextual information is typically shown to be helpful for acoustic modeling. Recently, we proposed a RNN model called minimal gated recurrent unit with input projection (mGRUIP), in which a context module namely temporal convolution, is specifically designed to model the future context. This model, mGRUIP with context module (mGRUIP-Ctx), has been shown to be able of utilizing the future context effectively, meanwhile with quite low model latency and computation cost. In this paper, we continue to improve mGRUIP-Ctx with two revisions: applying BN methods and enlarging model context. Experimental results on two Mandarin ASR tasks (8400 hours and 60K hours) show that, the revised mGRUIP-Ctx outperform LSTM with a large margin (11% to 38%). It even performs slightly better than a superior BLSTM on the 8400h task, with 33M less parameters and just 290ms model latency.
@article{arxiv.1811.10169,
title = {Improving Gated Recurrent Unit Based Acoustic Modeling with Batch Normalization and Enlarged Context},
author = {Jie Li and Yahui Shan and Xiaorui Wang and Yan Li},
journal= {arXiv preprint arXiv:1811.10169},
year = {2018}
}