SPIDER: Lightweight Speaker Identification on Resource-Constrained Embedded Devices

Simple item page
dc.contributor.authorGallacher, Markus
dc.contributor.authorBoano, Carlo Alberto
dc.contributor.authorPillai, Arun Sankar Muttathu Sivasankara
dc.contributor.authorRoedig, Utz
dc.contributor.authorLunardi, Willian
dc.contributor.authorBaddeley, Michael
dc.contributor.funderTechnology Innovation Institute
dc.contributor.funderTaighde Éireann - Research Ireland
dc.date.accessioned2026-07-08T11:50:06Z
dc.date.available2026-07-08T11:50:06Z
dc.date.issued2026-05-10
dc.description.abstractVoice-based Speaker Identification (SI) can be framed as the problem of Closed-Set Speaker Identification (CSSI), recognizing a speaker from a known set, or OSSI, additionally recognizing unknown speakers. Precise and accurate Open-Set Speaker Identification (SI) can enable a variety of applications, ranging from human presence detection to authentication. Existing SI solutions are typically driven by deep learning approaches, which involve computationally demanding models often running in cloud back-ends. Enabling local SI models running directly on resource-constrained embedded devices can enable new use cases while preserving speaker privacy. In this work, we fill this gap and present SPIDER, a lightweight, on-device CSSI and OSSI solution capable of running on the off-the-shelf Nordic nRF52840 and nRF5340 system-on-chip microcontrollers, which feature as little as 256 and 512 kB of RAM, respectively, and 1 MB of flash memory. SPIDER is 16x-67x smaller than currently-available SI models, and yet, the 16x smaller version achieves a comparable accuracy of 94.33 % for CSSI and 91.8% for OSSI. Our evaluation across multiple datasets confirms the viability of performing accurate SI directly on resource-constrained embedded devices using only low-cost microphones. To foster further research and development, we open source our implementation of SPIDER, empowering the community to explore new SI use cases where cloud connectivity or backhaul infrastructure is impractical or undesirable.en
dc.description.sponsorshipTechnology Innovation Institute|SPiDRproject Research Ireland|19/FFP/6775
dc.description.versionPublished Version
dc.format.extent14
dc.format.mimetypeapplication/pdfen
dc.identifier.authororcidGallacher, Markus
dc.identifier.authororcidBoano, Carlo Alberto
dc.identifier.authororcidPillai, Arun Sankar Muttathu Sivasankara
dc.identifier.authororcidRoedig, Utz§0000-0002-4020-0889
dc.identifier.authororcidLunardi, Willian
dc.identifier.authororcidBaddeley, Michael
dc.identifier.citationGallacher, M, Boano, C A, Pillai, A S M S, Roedig, U, Lunardi, W & Baddeley, M 2026, SPIDER: Lightweight Speaker Identification on Resource-Constrained Embedded Devices. in SenSys 2026 - Proceedings of the 2026 ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems, Part of CPS-IoTWeek 2026, Saint Malo, France 11 - 14 May 2026. SenSys 2026 - Proceedings of the 2026 ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems, Part of CPS-IoTWeek 2026, Association for Computing Machinery, Inc, pp. 1316-1329, International Conference on Embedded Artificial Intelligence and Sensing Systems, SenSys 2026, Saint Malo, France, 11/05/26. https://doi.org/10.1145/3774906.3800492
dc.identifier.doi10.1145/3774906.3800492
dc.identifier.endpage1329
dc.identifier.isbn9798400723094
dc.identifier.otherORCID: /0000-0002-4020-0889/work/220111854
dc.identifier.startpage1316
dc.identifier.urihttps://hdl.handle.net/10468/19025
dc.language.isoen
dc.publisherAssociation for Computing Machinery, Inc
dc.relation.ispartofseriesSenSys 2026 - Proceedings of the 2026 ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems, Part of CPS-IoTWeek 2026
dc.rights© 2026, the owner/author(s).
dc.rights.accessrightsopen access
dc.rights.licensenameAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.statusPeer reviewed
dc.subjectDatasets
dc.subjectEmbedded AI
dc.subjectInformation processing
dc.subjectLightweight models
dc.subjectMachine learning
dc.subjectOpen-set speaker identification
dc.subject[ComputerScience]
dc.titleSPIDER: Lightweight Speaker Identification on Resource-Constrained Embedded Devicesen
dc.typeConference item
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
3774906.3800492.pdf
Size:
868.49 KB
Format:
Adobe Portable Document Format
Download
Collections
School of Computer Science and Information Technology