ISCA Archive CHiME 2018
ISCA Archive CHiME 2018

The USTC-iFlytek systems for CHiME-5 Challenge

Jun Du, Tian Gao, Lei Sun, Feng Ma, Yi Fang, Di-Yuan Liu, Qiang Zhang, Xiang Zhang, Hai-Kun Wang, Jia Pan, Jian-Qing Gao, Chin-Hui Lee, Jing-Dong Chen

This report describes our submission to the fifth CHiME Challenge. The main technical points of our system include the deep learning based speech enhancement and separation, training data augmentation via different versions of the official training data, SNR-based array selection, front-end model fusion, acoustic model fusion, and language model fusion. Tested on the development test set, our best system for single-array track using official LM has yielded a 37.7% WER relative reduction over the results given by official baseline system.

doi: 10.21437/CHiME.2018-3

Cite as: Du, J., Gao, T., Sun, L., Ma, F., Fang, Y., Liu, D.-Y., Zhang, Q., Zhang, X., Wang, H.-K., Pan, J., Gao, J.-Q., Lee, C.-H., Chen, J.-D. (2018) The USTC-iFlytek systems for CHiME-5 Challenge. Proc. 5th International Workshop on Speech Processing in Everyday Environments (CHiME 2018), 11-15, doi: 10.21437/CHiME.2018-3

  author={Jun Du and Tian Gao and Lei Sun and Feng Ma and Yi Fang and Di-Yuan Liu and Qiang Zhang and Xiang Zhang and Hai-Kun Wang and Jia Pan and Jian-Qing Gao and Chin-Hui Lee and Jing-Dong Chen},
  title={{The USTC-iFlytek systems for CHiME-5 Challenge}},
  booktitle={Proc. 5th International Workshop on Speech Processing in Everyday Environments (CHiME 2018)},