Knowledge Distillation via Module Replacing for Automatic Speech Recognition with Recurrent Neural Network Transducer

Kaiqi Zhao 0002, Hieu Nguyen, Animesh Jain, Nathan Susanj, Athanasios Mouchtaris, Lokesh Gupta, Ming Zhao. Knowledge Distillation via Module Replacing for Automatic Speech Recognition with Recurrent Neural Network Transducer. In Hanseok Ko, John H. L. Hansen, editors, Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022. pages 4436-4440, ISCA, 2022. [doi]

@inproceedings{0002NJSMGZ22,
  title = {Knowledge Distillation via Module Replacing for Automatic Speech Recognition with Recurrent Neural Network Transducer},
  author = {Kaiqi Zhao 0002 and Hieu Nguyen and Animesh Jain and Nathan Susanj and Athanasios Mouchtaris and Lokesh Gupta and Ming Zhao},
  year = {2022},
  doi = {10.21437/Interspeech.2022-500},
  url = {https://doi.org/10.21437/Interspeech.2022-500},
  researchr = {https://researchr.org/publication/0002NJSMGZ22},
  cites = {0},
  citedby = {0},
  pages = {4436-4440},
  booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022},
  editor = {Hanseok Ko and John H. L. Hansen},
  publisher = {ISCA},
}