Projected Minimal Gated Recurrent Unit for Speech Recognition
Projected Minimal Gated Recurrent Unit for Speech Recognition
复制标题
用于语音识别的预计最小门控循环单元
DOI：
10.1109/access.2020.3041477
复制
发表时间：
2020
期刊：
影响因子：
3.9
通讯作者：
Yan Jiaxuan
中科院分区：
文献类型：
--
作者：
Feng Renjian;Jiang Weijie;Yu Ning;Wu Yinfeng;Yan Jiaxuan
Recurrent neural network (RNN) has the ability to learn long-term dependencies, which makes it suitable for acoustic modeling in speech recognition. In this paper, we revise RNN model used in acoustic modeling, namely, mGRUIP with Context module (mGRUIP-Ctx), and propose an advanced model which named Projected minimal Gated Recurrent Unit (PmGRU). The paper demonstrates two major contributions: firstly, in the case that adding context information to context module in mGRUIP-Ctx will bring about large amount of parameter, we propose to insert a smaller output projection layer after the mGRUIP-Ctx cell’s output to form the PmGRU, which is inspired by the idea of low-rank decomposition of matrix. The output projection layer has been proved to be able to save most of the effective information with the reduction of model parameters. Secondly, in the case that too much context information of previous layer introduced by context module will cause declining of model performance, we adjust the ratio of context information of the previous layer to the current layer by moving the position of batch normalization layer, and the final RNN model Normalization Projected minimal Gated Recurrent Unit (Norm-PmGRU) is generated. In the five automatic speech recognition (ASR) tasks, the Norm-PmGRU has been proved more effectively in the experiments compared with mGRUIP-Ctx, TDNN-OPGRU, TDNN-LSTMP and other RNN baseline acoustics models.
登录
查看更多内容
DOI：
10.1109/iscslp.2018.8706567
发表时间：
2018-11
期刊：
2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)
影响因子：
--
作者：
Jie Li;Yahui Shan;Xiaorui Wang;Yan Li
通讯作者：
Jie Li;Yahui Shan;Xiaorui Wang;Yan Li
DOI：
10.1109/icassp.2016.7472821
发表时间：
2016-03
期刊：
2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子：
--
作者：
Zhiyun Lu;Vikas Sindhwani;Tara N. Sainath
通讯作者：
Zhiyun Lu;Vikas Sindhwani;Tara N. Sainath
影响因子：
3.9
作者：
Peddinti, Vijayaditya;Wang, Yiming;Khudanpur, Sanjeev
通讯作者：
Khudanpur, Sanjeev
DOI：
10.1109/tsmc.2019.2946248
发表时间：
2021-06
期刊：
IEEE Transactions on Systems, Man, and Cybernetics: Systems
影响因子：
--
作者：
Hongjing Liang;Linchuang Zhang;Yonghui Sun;Tingwen Huang
通讯作者：
Hongjing Liang;Linchuang Zhang;Yonghui Sun;Tingwen Huang
影响因子：
3.9
作者：
M. Zorzi;A. Zanella;Alberto Testolin;Michele De Filippo De Grazia-Michele-De-Filippo-De-Grazia-7428476;M. Zorzi
通讯作者：
M. Zorzi;A. Zanella;Alberto Testolin;Michele De Filippo De Grazia-Michele-De-Filippo-De-Grazia-7428476;M. Zorzi