Large-Scale Unsupervised Pre-Training for End-to-End Spoken Language Understanding

Pengwei Wang, Liangchen Wei, Yong Cao, Jinghui Xie, Zaiqing Nie

Abstract

End-to-end Spoken Language Understanding (SLU) is proposed to infer the semantic meaning directly from audio features without intermediate text representation. In this paper, we explore unsupervised pre-training for End-to-end SLU models by learning representations from large-scale raw audios. The pre-trained model preserves semantic features which benefit the downstream SLU tasks as the learned model weights are further fine-tuned on the task specific training data. Our approach out-perform the state-of-the-art end-to-end SLU system with over 18.33% error reduction.
BibTeX
@inproceedings{wang2020large,
  author = {Pengwei Wang and Liangchen Wei and Yong Cao and Jinghui Xie and Zaiqing Nie},
  title = {{Large-Scale Unsupervised Pre-Training for End-to-End Spoken Language Understanding}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2020},
  doi = {10.1109/icassp40776.2020.9053163},
}

Loading related content...

Figure