Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR

Naoyuki Kanda, Zhong Meng, Liang Lu, Yashesh Gaur, Xiaofei Wang, Zhuo Chen, Takuya Yoshioka. Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021. pages 6503-6507, IEEE, 2021. [doi]

@inproceedings{KandaMLGWCY21,
  title = {Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR},
  author = {Naoyuki Kanda and Zhong Meng and Liang Lu and Yashesh Gaur and Xiaofei Wang and Zhuo Chen and Takuya Yoshioka},
  year = {2021},
  doi = {10.1109/ICASSP39728.2021.9415062},
  url = {https://doi.org/10.1109/ICASSP39728.2021.9415062},
  researchr = {https://researchr.org/publication/KandaMLGWCY21},
  cites = {0},
  citedby = {0},
  pages = {6503-6507},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2021, Toronto, ON, Canada, June 6-11, 2021},
  publisher = {IEEE},
  isbn = {978-1-7281-7605-5},
}