Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities

Andros Tjandra, Nayan Singhal, David Zhang, Ozlem Kalinli, Abdelrahman Mohamed, Duc Le, Michael L. Seltzer. Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities. In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023. pages 1-5, IEEE, 2023. [doi]

@inproceedings{TjandraSZKMLS23,
  title = {Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities},
  author = {Andros Tjandra and Nayan Singhal and David Zhang and Ozlem Kalinli and Abdelrahman Mohamed and Duc Le and Michael L. Seltzer},
  year = {2023},
  doi = {10.1109/ICASSP49357.2023.10094667},
  url = {https://doi.org/10.1109/ICASSP49357.2023.10094667},
  researchr = {https://researchr.org/publication/TjandraSZKMLS23},
  cites = {0},
  citedby = {0},
  pages = {1-5},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023},
  publisher = {IEEE},
  isbn = {978-1-7281-6327-7},
}