Hearing people speak in different accents biases voice discrimination
Bibliographic record
Abstract
Voice discrimination is a fundamentally different task when matching utterances than when matching identity across different words. Discriminating between speakers of different languages makes the task even harder because unfamiliar languages contain different phonemes that are less easily matched. Discriminating between people with different accents may also be difficult as even if the same words are uttered, the phonemes are different. To test this, we created a set of voices using voice cloning that have the same or different identity or accent (UK, Poland, and China) and speaking different phrases. We tested how accent, sentences, and identify affected bias to conflate different identities as the same person. Contrasting identity between different and same increased bias to judge people as the same by about 62%. Contrasting accent between different and same independently increased bias to judge people as the same by about 10%. Contrasting between different and same sentences, changed bias to label people the same more when the accents were different than when they were the same. Our results are consistent with the idea that we are biased to think people typically speak with one accent. Thus, accents affect voice discrimination independently of language familiarity.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".