MétaCan
Menu
Back to cohort

Exploring potential age, gender, and first language bias when using Google Voice Typing (GVT) for automatic scoring systems in pronunciation placement tests

2024· article· en· W4405576498 on OpenAlexfundaboutno aff

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldHealth Professions
TopicInterpreting and Communication in Healthcare
Canadian institutionsnot available
FundersUniversité du Québec à Montréal
KeywordsPronunciationDictationComputer scienceTest (biology)Task (project management)Speech recognitionArtificial intelligenceNatural language processingPsychologyAudiologyLinguisticsMedicineEngineering

Abstract

fetched live from OpenAlex

Dictation technology using automatic speech recognition (ASR), such as Google Voice Typing (GVT), has shown promise in scoring pronunciation placement tests, with strong correlations to human rater scores. However, potential biases in these systems must be investigated to ensure fair and accurate assessments. This quantitative study examined gender, first language (L1), and age biases in GVT-based scoring of a pronunciation placement test. Existing recordings of pronunciation placement tests of 1000 university-level English second language students in Canada were examined. The test takers completed a timed task of reading five increasingly complex sentences which were scored by human raters. Regression analyses were conducted with the GVT scores predicting human-rater scores, with age, gender, and L1 input as moderators. Results revealed no significant gender or L1 bias; however, test takers aged 29 and younger were disadvantaged due to an age bias. We conclude that GVT could serve as a reliable tool for scoring pronunciation placement tests if scores are adjusted to mitigate the identified age bias.

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)0.017
metaresearch head score (Gemma)0.063
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.017
Threshold uncertainty score0.088

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0170.063
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.001

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 head0.399
GPT teacher head0.458
Teacher spread0.059 · 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 designObservational
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

Citations0
Published2024
Admission routes2
Has abstractyes

Explore more

Same topicInterpreting and Communication in HealthcareFrench-language works237,207