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.
@article{arxiv.2402.13076,
title = {Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions},
author = {Yang Li and Yuan Shangguan and Yuhao Wang and Liangzhen Lai and Ernie Chang and Changsheng Zhao and Yangyang Shi and Vikas Chandra},
journal= {arXiv preprint arXiv:2402.13076},
year = {2025}
}
Comments
Proceedings of Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics - Industry Track (NAACL), 2025