Title | ||
---|---|---|
Improving Gated Recurrent Unit Based Acoustic Modeling with Batch Normalization and Enlarged Context. |
Abstract | ||
---|---|---|
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 namelytemporal 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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/iscslp.2018.8706567 | 2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP) |
Keywords | DocType | Volume |
Context modeling,Logic gates,Mathematical model,Task analysis,Computational modeling,Switches,Convolution | Conference | abs/1811.10169 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jie Li | 1 | 44 | 2.43 |
Yahui Shan | 2 | 0 | 2.03 |
Xiaorui Wang | 3 | 19 | 6.13 |
Yan Li | 4 | 365 | 35.61 |