@inproceedings{nussbaum-thom-etal-2023-application,
    title = "Application-Agnostic Language Modeling for On-Device {ASR}",
    author = "Nussbaum-thom, Markus  and
      Verwimp, Lyan  and
      Oualil, Youssef",
    editor = "Sitaram, Sunayana  and
      Beigman Klebanov, Beata  and
      Williams, Jason D",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.acl-industry.25/",
    doi = "10.18653/v1/2023.acl-industry.25",
    pages = "268--275",
    abstract = "On-device automatic speech recognition systems face several challenges compared to server-based systems. They have to meet stricter constraints in terms of speed, disk size and memory while maintaining the same accuracy. Often they have to serve several ap- plications with different distributions at once, such as communicating with a virtual assistant and speech-to-text. The simplest solution to serve multiple applications is to build application-specific (language) models, but this leads to an increase in memory. Therefore, we explore different data- and architecture-driven language modeling approaches to build a single application-agnostic model. We propose two novel feed-forward architectures that find an optimal trade off between different on-device constraints. In comparison to the application-specific solution, one of our novel approaches reduces the disk size by half, while maintaining speed and accuracy of the original model."
}