A comparison of procedures for the calculation of forensic likelihood ratios from acoustic–phonetic data: Multivariate kernel density (MVKD) versus Gaussian mixture model–universal background model (GMM–UBM)
- 1 February 2011
- journal article
- Published by Elsevier in Speech Communication
- Vol. 53 (2) , 242-256
Abstract
No abstract availableKeywords
This publication has 32 references indexed in Scilit:
- A response to the UK Position Statement on forensic speaker comparisonThe International Journal of Speech, Language and the Law, 2009
- Exploring the Discriminatory Potential of F0 Distribution Parameters in Traditional Forensic Speaker RecognitionThe International Journal of Speech, Language and the Law, 2009
- Forensic PhoneticsLanguage and Linguistics Compass, 2008
- Aural and automatic forensic speaker recognition in mismatched conditionsThe International Journal of Speech, Language and the Law, 2005
- An introduction to Bayesian credible intervals for sampling error in DNA profilesLaw, Probability and Risk, 2005
- Assessing uncertainty in DNA evidence caused by sampling effectsScience & Justice, 2002
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000
- Applying Logistic Regression to the Fusion of the NIST'99 1-Speaker SubmissionsDigital Signal Processing, 2000
- A hierarchy of propositions: deciding which level to address in caseworkScience & Justice, 1998
- Towards a uniform framework for reporting opinions in forensic science caseworkScience & Justice, 1998