Serialized Output Training for End-to-End Overlapped Speech Recognition

Naoyuki Kanda, Yashesh Gaur, Xiaofei Wang, Zhong Meng, Takuya Yoshioka. Serialized Output Training for End-to-End Overlapped Speech Recognition. In Helen Meng, Bo Xu 0011, Thomas Fang Zheng, editors, Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020. pages 2797-2801, ISCA, 2020. [doi]

@inproceedings{KandaGWMY20,
  title = {Serialized Output Training for End-to-End Overlapped Speech Recognition},
  author = {Naoyuki Kanda and Yashesh Gaur and Xiaofei Wang and Zhong Meng and Takuya Yoshioka},
  year = {2020},
  doi = {10.21437/Interspeech.2020-0999},
  url = {https://doi.org/10.21437/Interspeech.2020-0999},
  researchr = {https://researchr.org/publication/KandaGWMY20},
  cites = {0},
  citedby = {0},
  pages = {2797-2801},
  booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020},
  editor = {Helen Meng and Bo Xu 0011 and Thomas Fang Zheng},
  publisher = {ISCA},
}