I am currently a Master candidate at Department of Electronic Engineering, Tsinghua University(THUEE). Also I am a Research Intern at Key Lab of Speech Acoustics and Content Understanding, Institute of Acoustics(IOA), Chinese Academy of Sciences(CAS).

My research focuses on Artificial Neural Networks (especially recurrent neural networks) and Deep Learning , as well as their applications to Acoustic Modeling for Large Vocabulary Continuous Speech Recognition (LVCSR).


Time Education
Aug 2017 ~ Jul 2020 Master of Engineering at THUEE
Aug 2013 ~ Jul 2017 Bachelor of Engineering at THUEE

Selected Talks

2018-08 PIT in ICASSP (pdf)

2018-09 End-to-End ASR for Mandarin Chinese (pdf)


[Google Scholar]


Gaofeng Cheng, Lu Huang, Jiasong Sun, Yonghong Yan. “Bidirectional LSTM with Extended Input Context”, In Proceedings of ISCSLP 2018.

Gaofeng Cheng, Dan Povey, Lu Huang, Ji Xu, Sanjeev Khudanpur, Yonghong Yan. “Output-Gate Projected Gated Recurrent Unit for Speech Recognition,” In Proceedings of Interspeech 2018.


L. Huang, J. Xu, J. Sun, Y. Yang, “An Improved Residual LSTM Architecture for Acoustic Modeling,” 2017 2nd International Conference on Computer and Communication Systems (ICCCS), Krakow, Poland, 2017, pp. 101-105. doi: 10.1109/CCOMS.2017.8075276. Included in IEEE Xplore.

J. Zhang, L. Huang, J. Sun, “Keyword Spotting with Long Short-Term Memory Neural Network Architectures,” 2017 International Conference on Computer, Electronics and Communication Engineering (CECE), Sanya, China, 2017, pp. 58-64. doi: 10.12783/dtcse/cece2017/14374. Published by DEStech Transactions on Computer Science and Engineering.

All the papers can be written online using online latex editor: ShareLaTeX or Overleaf.


黄露, 杨毅, 孙甲松(清华大学). 一种残差长短期记忆循环神经网络的声学模型建模方法. 中国, CN107293288 A(公开号). 2017-10-24.