Cross-register speaker identification: The case of infant and adult directed speech
Bibliographic record
Abstract
The performance of automatic speaker recognition (ASR) systems decreases when training and test data are produced in different social situations (speech registers). The present research tested ASR performance across adult- and infant-directed speech registers (ADS and IDS respectively). IDS compared to ADS is generally characterized by higher and more variable F0, hyper-articulated vowels and higher segment duration and variability. Our dataset consisted of 12 sentences read by 10 Swiss-German mothers to their infants (IDS register) and to an adult experimenter (ADS register). ASR was performed when training and test registers were the same (within register) and when they varied (between register) in 3 experiments. Experiment I used segmental features such as MFCCs and their deltas. Results revealed considerable recognition rate within register (87%) that dropped to about half between registers (44%). This suggests that the variability between IDS and ADS poses challenges on ASR. Experiment II (in progress) uses prosodic features such as F0 statistics, local and long term variations of F0, intensity variations and energy of the frame for the identification. In experiment III, segmental and prosodic features are combined to model the classifier for the identification done in the previous experiments.
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 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".