Suyoun Kim, Ke Li, Lucas Kabela, Ron Huang, Jiedan Zhu, Ozlem Kalinli, Duc Le. Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition. In Yoav Goldberg, Zornitsa Kozareva, Yue Zhang, editors, Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022. pages 5717-5722, Association for Computational Linguistics, 2022. [doi]
Abstract is missing.