Weijie Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Weijie Jiang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Jiaxuan Yan
Key Laboratory of Education Ministry for Precision Opto-Mechatronics Technology and the School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing, China
1 shared publication - Ning Yu
Key Laboratory of Education Ministry for Precision Opto-Mechatronics Technology, Beihang University, China
1 shared publication - Renjian Feng
Key Laboratory of Education Ministry for Precision Opto-Mechatronics Technology, Beihang University, China
1 shared publication - Yinfeng Wu
School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 1 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 215192-215201
Projected Minimal Gated Recurrent Unit for Speech Recognition
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.
- 1 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 215192-215201
Open AccessProjected Minimal Gated Recurrent Unit for Speech Recognition
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.