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

Wiebke Toussaint, Akhil Mathur, Aaron Yi Ding, Fahim Kawsar

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)
4 Downloads (Pure)

Abstract

When deploying machine learning (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.
Original languageEnglish
Title of host publicationSenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems
PublisherAssociation for Computing Machinery (ACM)
Pages439-445
Number of pages7
ISBN (Electronic)9781450390972
DOIs
Publication statusPublished - 2021
Event19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021 - Coimbra, Portugal
Duration: 15 Nov 202117 Nov 2021

Publication series

NameSenSys 2021 - Proceedings of the 2021 19th ACM Conference on Embedded Networked Sensor Systems

Conference

Conference19th ACM Conference on Embedded Networked Sensor Systems, SenSys 2021
Country/TerritoryPortugal
CityCoimbra
Period15/11/2117/11/21

Keywords

  • audio keyword spotting
  • embedded machine learning
  • fairness
  • pre-processing parameters

Fingerprint

Dive into the research topics of 'Characterising the Role of Pre-Processing Parameters in Audio-based Embedded Machine Learning'. Together they form a unique fingerprint.

Cite this