MétaCan
Menu
Back to cohort

Domestic Sound Classification with Deep Learning

2023· article· en· W4386919815 on OpenAlexaff
Zhenyu Zhang, Yichun Shen, Julio J. Valdés, Saiful Huq, Bruce Wallace, James R. Green, Pengcheng Xi, Rafik Goubran

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicMusic and Audio Processing
Canadian institutionsBruyèreNational Research Council CanadaCarleton University
Fundersnot available
KeywordsComputer scienceSound (geography)Deep learningArtificial intelligenceSpeech recognitionGeologyOceanography

Abstract

fetched live from OpenAlex

Smart sensing and AI technologies are playing an increasingly important role in supporting aging in place, including embedded microphone devices that can contribute to safety by recognizing home events that need attention. In this work, we study sound event detection through classifying different sources of sounds. Specifically, we study the performance of models applied to a dataset of recordings in a domestic environment. We propose a light-weight, VGG-like model with a customized loss function. Relative to existing methods, the proposed model has significantly reduced the number of parameters from 2.6M to 75K and is therefore effective for use with embedded devices. Our proposed model can be deployed on low-cost edge-computing devices and still achieves comparable performance as those from complex models.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.008
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0020.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0020.001
Insufficient payload (model declined to judge)0.0030.002

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 head0.032
GPT teacher head0.271
Teacher spread0.239 · 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; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

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

Citations1
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicMusic and Audio ProcessingFrench-language works237,207