@inproceedings{wu-etal-2024-deferred,
    title = "Deferred {NAM}: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming {ASR}",
    author = "Wu, Zelin  and
      Song, Gan  and
      Li, Christopher  and
      Rondon, Pat  and
      Meng, Zhong  and
      Velez, Xavier  and
      Wang, Weiran  and
      Caseiro, Diamantino  and
      Pundak, Golan  and
      Munkhdalai, Tsendsuren  and
      Chandorkar, Angad  and
      Prabhavalkar, Rohit",
    editor = "Yang, Yi  and
      Davani, Aida  and
      Sil, Avi  and
      Kumar, Anoop",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-industry.26/",
    doi = "10.18653/v1/2024.naacl-industry.26",
    pages = "315--323"
}