A
Andrzej Drygajlo
Researcher at École Polytechnique Fédérale de Lausanne
Publications - 119
Citations - 2475
Andrzej Drygajlo is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Speaker recognition & Biometrics. The author has an hindex of 27, co-authored 119 publications receiving 2399 citations.
Papers
More filters
Proceedings Article
Entropy Based Voice Activity Detection in Very Noisy Conditions
TL;DR: LTS1 Reference LTS-CONF-2001-039 Record created on 2006-06-14, modified on 2016-08-08.
Journal ArticleDOI
Robust estimation, interpretation and assessment of likelihood ratios in forensic speaker recognition
Joaquin Gonzalez-Rodriguez,Andrzej Drygajlo,Daniel Ramos-Castro,Marta Garcia-Gomar,Javier Ortega-Garcia +4 more
TL;DR: The Bayesian framework for interpretation of evidence when applied to forensic speaker recognition is introduced, and original contributions for the robust estimation of likelihood ratios are fully described, including TDLRA (target dependent likelihood ratio alignment), oriented to guarantee the presumption of innocence of suspected but non-perpetrators speakers.
Proceedings ArticleDOI
Local and global feature selection for on-line signature verification
TL;DR: The difference in the definition of class between signature verification and other pattern recognition tasks is exposed, and the classical Fisher ratio is extended to make it more robust to the small sample sizes typically found when dealing with global features and client enrollment time constraints for signature verification systems.
Journal ArticleDOI
Perceptual speech coding and enhancement using frame-synchronized fast wavelet packet transform algorithms
B. Carnero,Andrzej Drygajlo +1 more
TL;DR: This paper presents new wideband speech coding and integrated speech coding-enhancement systems based on frame-synchronized fast wavelet packet transform algorithms and formulates temporal and spectral psychoacoustic models of masking adapted to wavelet packets analysis.
Proceedings ArticleDOI
Palm vein recognition with Local Binary Patterns and Local Derivative Patterns
TL;DR: A promising new approach based on local texture patterns is proposed and tests show that the best adapted LDP descriptors consistently outperform their LBP counterparts in both palm vein verification and identification.