Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition

Zhengkun Tian, Jiangyan Yi, Jianhua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen


Non-autoregressive transformer models have achieved extremely fast inference speed and comparable performance with autoregressive sequence-to-sequence models in neural machine translation. Most of the non-autoregressive transformers decode the target sequence from a predefined-length mask sequence. If the predefined length is too long, it will cause a lot of redundant calculations. If the predefined length is shorter than the length of the target sequence, it will hurt the performance of the model. To address this problem and improve the inference speed, we propose a spike-triggered non-autoregressive transformer model for end-to-end speech recognition, which introduces a CTC module to predict the length of the target sequence and accelerate the convergence. All the experiments are conducted on a public Chinese mandarin dataset AISHELL-1. The results show that the proposed model can accurately predict the length of the target sequence and achieve a competitive performance with the advanced transformers. What’s more, the model even achieves a real-time factor of 0.0056, which exceeds all mainstream speech recognition models.


 DOI: 10.21437/Interspeech.2020-2086

Cite as: Tian, Z., Yi, J., Tao, J., Bai, Y., Zhang, S., Wen, Z. (2020) Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition. Proc. Interspeech 2020, 5026-5030, DOI: 10.21437/Interspeech.2020-2086.


@inproceedings{Tian2020,
  author={Zhengkun Tian and Jiangyan Yi and Jianhua Tao and Ye Bai and Shuai Zhang and Zhengqi Wen},
  title={{Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={5026--5030},
  doi={10.21437/Interspeech.2020-2086},
  url={http://dx.doi.org/10.21437/Interspeech.2020-2086}
}