@inproceedings{li-etal-2025-breaking,
    title = "Breaking Down Power Barriers in On-Device Streaming {ASR}: Insights and Solutions",
    author = "Li, Yang  and
      Shangguan, Yuan  and
      Wang, Yuhao  and
      Lai, Liangzhen  and
      Chang, Ernie  and
      Zhao, Changsheng  and
      Shi, Yangyang  and
      Chandra, Vikas",
    editor = "Chen, Weizhu  and
      Yang, Yi  and
      Kachuee, Mohammad  and
      Fu, Xue-Yong",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-industry.50/",
    pages = "616--626",
    ISBN = "979-8-89176-194-0",
    abstract = "Power consumption plays a crucial role in on-device streaming speech recognition, significantly influencing the user experience. This study explores how the configuration of weight parameters in speech recognition models affects their overall energy efficiency. We found that the influence of these parameters on power consumption varies depending on factors such as invocation frequency and memory allocation. Leveraging these insights, we propose design principles that enhance on-device speech recognition models by reducing power consumption with minimal impact on accuracy. Our approach, which adjusts model components based on their specific energy sensitivities, achieves up to 47{\%} lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods."
}