Xingcheng Song

According to our database, Xingcheng Song authored at least 3 papers between 2019 and 2020.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2020

SpecSwap: A Simple Data Augmentation Method for End-to-End Speech Recognition.

Xingcheng Song, Zhiyong Wu, Yiheng Huang, Dan Su, Helen Meng

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

A Random Gossip BMUF Process for Neural Language Modeling.

Yiheng Huang, Jinchuan Tian, Lei Han, Guangsen Wang, Xingcheng Song, Dan Su, Dong Yu

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks.

Xingcheng Song, Guangsen Wang, Zhiyong Wu, Yiheng Huang, Dan Su, Dong Yu, Helen Meng

CoRR, 2019