Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems

Vishal Sunder, Eric Fosler-Lussier, Samuel Thomas 0001, Hong-Kwang Kuo, Brian Kingsbury. Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems. 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 2683-2687, ISCA, 2022. [doi]

@inproceedings{SunderF0KK22,
  title = {Tokenwise Contrastive Pretraining for Finer Speech-to-BERT Alignment in End-to-End Speech-to-Intent Systems},
  author = {Vishal Sunder and Eric Fosler-Lussier and Samuel Thomas 0001 and Hong-Kwang Kuo and Brian Kingsbury},
  year = {2022},
  doi = {10.21437/Interspeech.2022-239},
  url = {https://doi.org/10.21437/Interspeech.2022-239},
  researchr = {https://researchr.org/publication/SunderF0KK22},
  cites = {0},
  citedby = {0},
  pages = {2683-2687},
  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},
}