MétaCan
Menu
Back to cohort
Record W1981517541 · doi:10.1121/1.4877151

Using criterio voice familiarity to augment the accuracy of speaker identification in voice lineups

2014· article· en· W1981517541 on OpenAlexaff
Julien Plante-Hébert, Victor J. Boucher

Bibliographic record

VenueThe Journal of the Acoustical Society of America · 2014
Typearticle
Languageen
FieldComputer Science
TopicSpeech Recognition and Synthesis
Canadian institutionsUniversité de Montréal
Fundersnot available
KeywordsPsychologySpeaker identificationIdentification (biology)SyllableSpeech recognitionSemitoneDuration (music)AudiologySpeaker recognitionComputer scienceAcoustics

Abstract

fetched live from OpenAlex

Voice familiarity is a principal factor underlying the apparent superiority of human-based vs machine-based speaker identification. Our study evaluates the effects of voice familiarity on speaker identification in voice lineups by using a Familiarity Index that considers (1) recency (the time of last spoken contact), (2) duration of spoken contact, and (3) frequency of spoken contact. Three separate voice-lineups were designed each containing ten male voices with one target voice that was more or less familiar to individual listeners (13 per lineup, n = 39 listeners in all). The stimuli consisted in several verbal expressions varying in length, all of which reflected a similar dialect and the voices presented a similar speaking fundamental frequency to within one semitone. The main results showed high rates of correct target voice identification across lineups (>99%) when listeners were presented with voices that were highly familiar in terms of all three indices of recency, duration of contact, and frequency of contact. Secondary results showed that the length of the verbal stimuli had little impact on identification rates beyond a four-syllable string.

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.929
Threshold uncertainty score0.286

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.000
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 head0.303
Teacher spread0.265 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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
Published2014
Admission routes1
Has abstractyes

Explore more

Same venueThe Journal of the Acoustical Society of AmericaSame topicSpeech Recognition and SynthesisFrench-language works237,207