The distribution of calibrated likelihood-ratios in speaker recognition
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
This paper studies properties of the score distributions of calibrated log-likelihood-ratios that are used in automatic speaker recognition.We derive the essential condition for calibration that the log likelihood ratio of the log-likelihood-ratio is the log-likelihood-ratio.We then investigate what the consequence of this condition is to the probability density functions (PDFs) of the loglikelihood-ratio score.We show that if the PDF of the non-target distribution is Gaussian, then the PDF of the target distribution must be Gaussian as well.The means and variances of these two PDFs are interrelated, and determined completely by the discrimination performance of the recognizer characterized by the equal error rate.These relations allow for a new way of computing the offset and scaling parameters for linear calibration, and we derive closed-form expressions for these and show that for modern i-vector systems with PLDA scoring this leads to good calibration, comparable to traditional logistic regression, over a wide range of system performance.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The Comparison and Evaluation of Forecasters
DeGroot, M. H., & Fienberg, S. E. (1983) · The Statistician · doi:10.2307/2987588 · Cited by 604 · cited 1×
“Since around 2004 [1,2] the concept of calibration in speaker recognition has been generalized to a range of operating points by using proper scoring rules [17] to evaluate probabilistic statements about whether a trial is a same-speaker (target) or different-speaker (non-target) trial.”
BackgroundAn Introduction to Application-Independent Evaluation of Speaker Recognition Systems
van Leeuwen, D. A., & Brümmer, N. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-74200-5_19 · Cited by 179
Self-citation
Cited by
Text-dependent speaker verification: Classifiers, databases and RSR2015
Larcher, A., Lee, K. A., Ma, B., & Li, H. (2014) · Speech Communication · doi:10.1016/j.specom.2014.03.001 · Cited by 237
“For these reasons, a large scientific community focuses on text-independent speaker verification, despite the commercial potential of text-dependent speaker verification (Lee et al., 2013b; He´bert and Boies, 2005; Wagner et al., 2006; Dialogues Spotlight Technology, 2000; Gu and Thomas, 1998).”
BackgroundMethodInfluentialA guideline for the validation of likelihood ratio methods used for forensic evidence evaluation
Meuwly, D., Ramos, D., & Haraksim, R. (2017) · Forensic Science International · doi:10.1016/j.forsciint.2016.03.048 · Cited by 131
Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals
Kinnunen, T., Delgado, H., Evans, N., Lee, K. A., Vestman, V., Nautsch, A., Todisco, M., Wang, X., Sahidullah, M., Yamagishi, J., et al. (2020) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2020.3009494 · Cited by 108
Avoiding overstating the strength of forensic evidence: Shrunk likelihood ratios/Bayes factors
Morrison, G. S., & Poh, N. (2018) · Science & Justice · doi:10.1016/j.scijus.2017.12.005 · Cited by 47
Calibration of score based likelihood ratio estimation in automated forensic facial image comparison
Rodriguez, A. M., Geradts, Z., & Worring, M. (2022) · Forensic Science International · doi:10.1016/j.forsciint.2022.111239 · Cited by 19
From Biometric Scores to Forensic Likelihood Ratios
Ramos, D., Krish, R. P., Fierrez, J., & Meuwly, D. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-50673-9_14 · Cited by 18
t-EER: Parameter-free tandem evaluation of countermeasures and biometric comparators
Kinnunen, T. H., Lee, K. A., Tak, H., Evans, N., & Nautsch, A. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3313648 · Cited by 4
“Apart from some special cases, such as as Gaussian score PDFs with known parameters [39], [40], neither the EER nor the EER threshold have closed-form solutions, hence they are determined empirically from the operating point at which the empirical miss and false alarm functions intersect.”
Background
Metadata
- Authors
- Leeuwen, D. A. V., & Brümmer, N.
- Venue
- Interspeech 2013
- Publisher
- ISCA
- Published
- 2013-08-25
- Pages
- 1619-1623
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2101587318
- Cited by
- 68
- References
- 2
- FWCI
- 3.69
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.