Bilingual talker identification with spontaneous speech in Cantonese and English: The role of language-specific knowledge
Bibliographic record
Abstract
Previous research has shown that implicit or explicit knowledge about a language lends itself to improved talker recognition performance. In the context of this language familiarity effect, it is apparent that bilinguals are better at generalizing voice learning across their known languages compared to monolingual listeners [Orena et al., JASA, 146 (2019)]. Other work suggests that training in an unknown language generalizes to a known language more robustly than the reverse [Winters et al., JASA 123 (2008)]. The current study launches from these previous studies. This project uses excerpted Cantonese and English snippets from spontaneous interview speech from Cantonese-English bilinguals in a talker identification training experiment with Cantonese-English bilingual listeners and bilingual listeners with no knowledge of Cantonese (or related languages). Listeners are assigned to either Cantonese or English training, and then all listeners are tested on both Cantonese and English utterances to assess learning for the trained language and generalization to the bilingual's second language. Results of a multilingual questionnaire quantify listeners' code-switching abilities and multilingual competence, which, given prior research, should account for some individual differences. Using spontaneous productions, as opposed to read speech, improves the ecological validity of this research and broadens its implications.
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 | 0.004 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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.
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".