MétaCan
Menu
Back to cohort

Low-Power Real-Time Keyword Spotting for Autonomous Edge Devices

2025· article· W4417169656 on OpenAlexaff
Michael Grzybek, Andrew Comtois, Masoud Askariraad, Stefano Gregori

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicSpeech Recognition and Synthesis
Canadian institutionsUniversity of Guelph
Fundersnot available
KeywordsKeyword spottingDynamic time warpingFeature extractionSignal processingFeature (linguistics)Latency (audio)Enhanced Data Rates for GSM EvolutionKey (lock)Power consumptionWindow (computing)

Abstract

fetched live from OpenAlex

Described in this paper is a real-time keyword spotting system built on a low-power ARM microcontroller. This prototype utilizes an MFCC-based feature extraction method in conjunction with dynamic time warping for keyword comparison. Using the CMSIS-DSP library, optimized digital signal processing techniques as well as a real-time computing architecture allow for a noise-robust keyword recognition system. Up to 95% keyword recognition accuracy is observed, while 18.85 mW and 6.62 mW of power consumption are achieved in the run and idle modes, respectively. The recognition latency after recording is only 64 ms on average. This system widens the applications of both speech recognition tasks and IoT devices by creating an efficient edge computing system allowing for use in hands-free, control-oriented use cases.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Other · Consensus signal: none
Teacher disagreement score0.952
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0040.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.017
GPT teacher head0.267
Teacher spread0.251 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; both teacher heads agree on what is shown here.

Study designOther design
Domainnot available
GenreOther

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicSpeech Recognition and SynthesisFrench-language works237,207