ACM SenSys 2021

Characterising the Role of Pre-Processing Parameters in Audio-based Embedded Machine Learning

Abstract:

When deploying ML models on embedded and IoT devices, performance 
encompasses more than an accuracy metric: inference latency, 
energy consumption, and model fairness are necessary to ensure 
reliable performance under heterogeneous and resource-constrained 
operating conditions. To this end, prior research has studied 
model-centric approaches, such as tuning the hyperparameters of 
the model during training and later applying model compression 
techniques to tailor the model to the resource needs of an 
embedded device. In this paper, we take a data-centric view of 
embedded ML and study the role that pre-processing parameters in 
the data pipeline can play in balancing the various performance 
metrics of an embedded ML system. Through an in-depth case study 
with audio-based keyword spotting (KWS) models, we show that 
pre-processing parameter tuning is a remarkable tool that model 
developers can adopt to trade-off between a model's accuracy, 
fairness, and system efficiency, as well as to make an embedded 
ML model resilient to unseen deployment conditions.


Pre-camera PDF 

ACM Open Access

@inproceedings{Toussaint:SenSysAI2021,
 author = {Toussaint, Wiebke and Mathur, Akhil and Ding, Aaron Yi and Kawsar, Fahim},
 title = {Characterising the Role of Pre-Processing Parameters in Audio-based Embedded Machine Learning},
 booktitle = {Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems},
 pages = {439-445},
 series = {SenSys '21},
 year = {2021},
 url = {https://doi.org/10.1145/3485730.3493448},
 doi = {10.1145/3485730.3493448},
 publisher = {ACM}
}

Wiebke Toussaint, Akhil Mathur, Aaron Yi Ding, and Fahim Kawsar. 2021. "Characterising the Role of Pre-Processing Parameters in Audio-based Embedded Machine Learning". In Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems (SenSys '21). DOI:https://doi.org/10.1145/3485730.3493448