Memory-Efficient Training of RNN-Transducer with Sampled Softmax

Jaesong Lee, Lukas Lee, Shinji Watanabe 0001. Memory-Efficient Training of RNN-Transducer with Sampled Softmax. 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 4441-4445, ISCA, 2022. [doi]

@inproceedings{LeeL022,
  title = {Memory-Efficient Training of RNN-Transducer with Sampled Softmax},
  author = {Jaesong Lee and Lukas Lee and Shinji Watanabe 0001},
  year = {2022},
  doi = {10.21437/Interspeech.2022-787},
  url = {https://doi.org/10.21437/Interspeech.2022-787},
  researchr = {https://researchr.org/publication/LeeL022},
  cites = {0},
  citedby = {0},
  pages = {4441-4445},
  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},
}