Qi Liu

Orcid: 0000-0003-3067-8333

Affiliations:
  • Shanghai Jiao Tong University, MoE Key Lab of Artificial Intelligence, Shanghai, China
  • Shanghai Jiao Tong University, Department of Computer Science and Engineering, SpeechLab, Shanghai, China


According to our database1, Qi Liu authored at least 11 papers between 2015 and 2020.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2020
Neural Network Language Model Compression With Product Quantization and Soft Binarization.
IEEE ACM Trans. Audio Speech Lang. Process., 2020

Modular End-to-End Automatic Speech Recognition Framework for Acoustic-to-Word Model.
IEEE ACM Trans. Audio Speech Lang. Process., 2020

An Investigation on Deep Learning with Beta Stabilizer.
CoRR, 2020

An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models.
Proceedings of the Natural Language Processing and Chinese Computing, 2020

Neural Lattice Search for Speech Recognition.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Addressing the Polysemy Problem in Language Modeling with Attentional Multi-Sense Embeddings.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
Highly Efficient Neural Network Language Model Compression Using Soft Binarization Training.
Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2019

2018
Noise Robust Speech Recognition on Aurora4 by Humans and Machines.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

On Modular Training of Neural Acoustics-to-Word Model for LVCSR.
Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017
Future vector enhanced LSTM language model for LVCSR.
Proceedings of the 2017 IEEE Automatic Speech Recognition and Understanding Workshop, 2017

2015
A study on effects of implicit and explicit language model information for DBLSTM-CTC based handwriting recognition.
Proceedings of the 13th International Conference on Document Analysis and Recognition, 2015


  Loading...