Adaptive threshold estimation for speaker verification systems
Bibliographic record
Abstract
This paper describes an adaptive threshold estimation mechanism for speaker authentication systems. The mechanism estimates speaker-dependent thresholds based on successful verifications considering the minimization of a relation-based cost function. Speaker authentication systems commonly use a threshold to decide whether a claimed identity matches a voice-print previously enrolled. Speaker independent threshold is a common option but it does not consider specific speaker characteristics that are relevant to achieve better system performance. Speaker dependent threshold on the contrary, uses speaker-specific data to estimate individual thresholds but the system performance can also suffer from suboptimal threshold conditioned by limited number of true scores. The algorithm reported in this paper starts with the speaker dependent threshold and use an adaptive algorithm to perform online re-estimation of the initial threshold based on speaker-dependent data. The threshold is re-estimated in each successful authentication transaction according to a custom-made confidence score. The reported technique keep the voice print up-to-date while is less sensitive to score outliers than traditional speaker dependent threshold. The algorithm provided a performance enhancement of up to 36.2% when compared to traditional speaker independent or dependent threshold using an ad-hoc database involving cell and land-line utterances from male and female speakers.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| 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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".