MétaCan
Menu
Back to cohort
Record W3161399843 · doi:10.31234/osf.io/v5uxf

VoiceLab: Automated Reproducible Acoustic Analysis

2020· preprint· en· W3161399843 on OpenAlex
David R. Feinberg, Oliver Cook

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldComputer Science
TopicMusic and Audio Processing
Canadian institutionsMcMaster University
Fundersnot available
KeywordsA priori and a posterioriBottleneckComputer scienceFocus (optics)SoftwareData scienceAsk priceArtificial intelligence

Abstract

fetched live from OpenAlex

Automated acoustical analysis is often difficult because a priori knowledge about vocalizers informs the search parameters of algorithms. As male and female voices differ on average, when measuring the voice, these a priori features unfortunately often manifest themselves by requiring the researcher to ask potentially invasive questions about the gender of the vocalizer, or assume the gender of the vocalizer in order to adjust analysis parameters. When adjusted by hand, this creates a research bottleneck. Furthermore, adjusted analysis parameters are rarely reported. With an increasing focus on inclusivity in research, as well as a focus on larger samples and big data, making new methods in voice analysis that can break these barriers accessible are essential. VoiceLab software offers automated acoustical analysis that does not require a priori knowledge of acoustic phonetics, idiosyncratic programming languages, or vocalizers’ gender, and automatically logs all analysis parameters. VoiceLab analyses are fully reproducible and require little to no knowledge about acoustical analysis from the user.

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.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.849
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0020.003
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.038
GPT teacher head0.292
Teacher spread0.254 · 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

Quick stats

Citations12
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicMusic and Audio ProcessingFrench-language works237,207