MétaCan
Menu
Back to cohort
Record W4392356050 · doi:10.29115/sp-2023-0022

Keep the noise down: On the performance of automatic speech recognition of voice-recordings in web surveys

2024· article· en· W4392356050 on OpenAlexafffund
Katharina Meitinger, Sabien van der Sluis, Matthias Schonlau

Bibliographic record

VenueSurvey Practice · 2024
Typearticle
Languageen
FieldSocial Sciences
TopicSurvey Methodology and Nonresponse
Canadian institutionsUniversity of Waterloo
FundersSocial Sciences and Humanities Research Council of Canada
KeywordsSpeech recognitionNoise (video)Computer scienceVoice activity detectionSpeech processingArtificial intelligence

Abstract

fetched live from OpenAlex

Voice-recordings are increasingly implemented in web surveys, but the resulting audio data need to be transcribed before analysis. Since manual coding is too time- and work-intensive, researchers often rely on automatic speech recognition (ASR) systems for the transcription of the voice-recordings. However, ASR tools might create partly incorrect transcriptions and potentially change the content of responses. If the ASR performance (i.e., accuracy and validity) differs by subgroup and contextual factors, a bias is introduced in the analysis of open-ended questions. We assessed the impact of sociodemographic and contextual factors on the accuracy and validity of ASR transcriptions with data from the Longitudinal Internet Studies for the Social Sciences (LISS) panel collected in December 2020. We find that background noise reduces the accuracy and validity of ASR transcriptions. In addition, validity improved when the respondent was alone during the survey. Fortunately, we did not find any evidence of systematic differences across subgroups (age, sex, education), devices or respondent location.

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)0.297
metaresearch head score (Gemma)0.723
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesMetaresearch
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.703
Threshold uncertainty score0.867

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.2970.723
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.004
Science and technology studies0.0010.004
Scholarly communication0.0060.006
Open science0.0030.004
Research integrity0.0030.002
Insufficient payload (model declined to judge)0.0020.002

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 head0.213
GPT teacher head0.426
Teacher spread0.213 · 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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.

Study designSimulation or modeling
DomainMethods
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

Citations2
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueSurvey PracticeSame topicSurvey Methodology and NonresponseFrench-language works237,207