Search
Search results for: SPEAKER AUTHENTICATION
-
Chemical composition analysis and authentication of whisky
PublicationW pracy przedstawiono informacje dotyczące porównania różnych rodzajów whisky i innych napojów alkoholowych, identyfikacji różnych rodzajów whisky, oceny jakości i potwierdzania autentyczności whisky. Ponadto w pracy omówiono różne techniki stosowane w analizie whisky, takie jak gazową i cieczową chromatografię z różnymi detektorami (FID, AED, UV-vis), nos elektroniczny, spektrometrię absorpcji atomowej i spektrometrię mas. Ponadto...
-
User authentication based on keystroke dynamics analysis
PublicationW pracy przedstawiono kilka metod, które można wykorzystać do uwierzytelniania użytkowników na podstawie rytmu pisania na klawiaturze. Dwie z opisanych metod wykorzystują miarę odległości zdefiniowaną do porównywania wpisywanych tekstów, natomiast trzecia analizuje parametry rozkładów cech wydobytych z wpisywanych tekstów. Algorytmy te zostały przetestowane na dwóch zbiorach danych. Ponadto oceniona została efektywność metody powstałej...
-
A model-based approach to analysis of authentication protocols.
PublicationW referacie przedstawiono zintegrowane podejście do analizy protokołów uwierzytelniania o nazwie Object-oriented Formal Authentication Protocol Security Analysis Framework (OF-APSAF). Podejście to jest zaprojektowane na bazie sprawdzonej metody formalnej CSP wraz z narzędziami ją wspierającymi: Casper oraz FDR. Jego integralną częścią jest półformalna zorientowana obiektowo technika modelowania protokołów, ich kontekstu oraz wymagań...
-
Application of dynamic time warping and cepstrograms to text-dependent speaker verification
PublicationThis work provides a description of an automatic speaker verification (ASV) system. In particular, it documents the evolution of all individual stages of the proposed ASV system design from the phase of preprocessing to an operational decision making system. The aim of this research was to achieve the system of the best safety and ease of use in view of users. The objective estimation of this target has been accomplished by assessing...
-
Open-Set Speaker Identification Using Closed-Set Pretrained Embeddings
PublicationThe paper proposes an approach for extending deep neural networks-based solutions to closed-set speaker identification toward the open-set problem. The idea is built on the characteristics of deep neural networks trained for the classification tasks, where there is a layer consisting of a set of deep features extracted from the analyzed inputs. By extracting this vector and performing anomaly detection against the set of known...
-
Liveness measurements using optical flow for biometric person authentication
PublicationAutomatyczne rozpoznawanie twarzy jest jedną z najpopularniejszych technik biometrycznych, jednak nawet najdokładniejsze algorytmy identyfikacji okażą się bezużyteczne, jeśli będzie można je oszukać, np. używając zdjęcia zamiast rzeczywistej osoby. Dlatego też odpowiedni pomiar żywotności jest niezwykle istotny. W pracy zaprezentowano metodę, która jest w stanie rozróżnić pomiędzy sekwencjami wideo pokazującymi żywe osoby oraz...
-
Usefulness of Keystroke Dynamics Features in User Authentication and Emotion Recognition
PublicationThe study presented in the article focuses on keystroke dynamics analysis applied to recognize emotional states and to authenticate users. An overview of some studies and applications in these areas is presented. Then, an experiment is described, i.e. the way of collecting data, extracting features, training classifiers and finding out the most appropriate feature subsets. The results show that it is difficult to indicate a universal...
-
Spenser Studies
Journals -
Concept of Multicriteria Aid of Choice of Threshold Value IN Biometrical Authentication System
Publication -
User Authentication by Eye Movement Features Employing SVM and XGBoost Classifiers
PublicationDevices capable of tracking the user’s gaze have become significantly more affordable over the past few years, thus broadening their application, including in-home and office computers and various customer service equipment. Although such devices have comparatively low operating frequencies and limited resolution, they are sufficient to supplement or replace classic input interfaces, such as the keyboard and mouse. The biometric...
-
An Automated Method for Biometric Handwritten Signature Authentication Employing Neural Networks
PublicationHandwriting biometrics applications in e-Security and e-Health are addressed in the course of the conducted research. An automated graphomotor analysis method for the dynamic electronic representation of the handwritten signature authentication was researched. The developed algorithms are based on dynamic analysis of electronically handwritten signatures employing neural networks. The signatures were acquired with the use of the...
-
Bożena Kostek prof. dr hab. inż.
People -
Speaker Recognition Using Convolutional Neural Network with Minimal Training Data for Smart Home Solutions
PublicationWith the technology advancements in smart home sector, voice control and automation are key components that can make a real difference in people's lives. The voice recognition technology market continues to involve rapidly as almost all smart home devices are providing speaker recognition capability today. However, most of them provide cloud-based solutions or use very deep Neural Networks for speaker recognition task, which are...
-
Eye Blink Based Detection of Liveness in Biometric Authentication Systems Using Conditional Random Fields
PublicationThe goal of this paper was to verify whether the conditional random fields are suitable and enough efficient for eye blink detection in user authentication systems based on face recognition with a standard web camera. To evaluate this approach several experiments were carried on using a specially developed test application and video database.
-
A Circuital Model of Electric Arc in a Circuit Breaker
PublicationThe paper presents a circuital model of arc in a circuit breaker. The model is intended to be used in simulations of the electric circuits transients. It was implemented in the ATP simulation program. The article presents also a few simulation examples of simple DC and AC circuit containing described arc model.
-
Taurine as a water structure breaker and protein stabilizer
PublicationThe enhancing effect on the water structure has been confirmed for most of the osmolytes exhibiting both stabilizing and destabilizing properties in regard to proteins. The presented work concerns osmolytes, which should be classified as “structure breaking” solutes: taurine and N,N,N-trimethyltaurine (TMT). Here, we combine FTIR spectroscopy, DSC calorimetry and DFT calculations to gain an insight into the interactions between...
-
Authentication of whisky due to its botanical origin and way of production by instrumental analysis and multivariate classification methods
PublicationHeadspacemass-spectrometry (HS-MS), mid infrared (MIR) and UV–vis spectroscopywere used to authenticate whisky samples from different origins and ways of production ((Irish, Spanish, Bourbon, TennesseeWhisky and Scotch). The collected spectra were processed with partial least-squares discriminant analysis (PLS-DA) to build the classification models. In all cases the five groups ofwhiskieswere distinguished, but the best resultswere...
-
Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice
PublicationThe vulnerability of the speaker identity verification system to attacks using voice cloning was examined. The research project assumed creating a model for verifying the speaker’s identity based on voice biometrics and then testing its resistance to potential attacks using voice cloning. The Deep Speaker Neural Speaker Embedding System was trained, and the Real-Time Voice Cloning system was employed based on the SV2TTS, Tacotron,...
-
Deep learning model for automated assessment of lexical stress of non-native english speakers
Publication -
Experimental studies of circuit breaker drives and mechanisms diagnostics
Publication -
MRM–MS of marker peptides and their abundance as a tool for authentication of meat species and meat cuts in single-cut meat products
PublicationThe abundance of protein markers in different types of meat cuts was explored in the context of authentication of raw meat (pork, beef and chicken) and processed meat products. Peptides originating from myoglobin (Mb) and myosin (My) were analyzed using multiple reaction monitoring mass spectrometry (MRM–MS). Analytical protocol was optimized for good repeatability (CV < 10%) and high sensitivity. The MS signal intensity of Mb...
-
Relative quantification of pork and beef in meat products using global and species-specific peptide markers for the authentication of meat composition
PublicationWe used global and species-specific peptide markers for a relative quantitative determination of pork and beef in raw and processed meat products made of the two meat species. Four groups of products were prepared (i.e., minced raw meats, sausages, raw and fried burgers) in order to represent products with different extents of food processing. In each group, the products varied in the pork/beef proportions. All products were analysed...
-
Speace frienly for the blind = Przestrzeń przyjazna dla niewidomych
PublicationThe article presents issues connected with accessibility of public space for people with eyesight disabilities. The use of the extravisual spatial stimuli in shaping the urban environment has been analysed. Spaces in which musltisensory spatial reception is feasible become user-friendly, as they come to meet the changing needs of their users. The article introduces a system of textures aiding spatial orientation, navigation and...
-
Grzegorz Boczkaj dr hab. inż.
People -
The influence of selected parameters of idd on vibrations of contact in ac hybrid breaker
PublicationWzrost mocy systemów zasilania na statkach wymaga poszukiwania nowych rozwiązań wyłączników dc oraz ac. Od kilku lat trwają prace nad modelowaniem ultra szybkiego hybrydowego wyłącznika prądu. Czas wyłączenia prądu wyłącznika zależy od wielu parametrów. W pracy przedstawiono wyniki badań eksperymentalnych i symulacyjnych wyłącznika ze szczególnym uwzględnieniem rezystancji zestyku.
-
Comparative Study of Self-Organizing Maps vs. Subjective Evaluation of Quality of Allophone Pronunciation for Nonnative English Speakers
PublicationThe purpose of this study was to apply Self-Organizing Maps to differentiate between the correct and the incorrect allophone pronunciations and to compare the results with subjective evaluation. Recordings of a list of target words, containing selected allophones of English plosive consonants, the velar nasal and the lateral consonant, were made twice. First, the target words were read from the list by 9 non-native speakers and...
-
Cobalt(II) tri-tert-butoxysilanethiolates with bidentate spacer ligands
PublicationOtrzymano szereg nowych tri-tert-butoksysilanotiolanów Co(II) z dwudonorowymi N,N'-ligandami takimi jak pirazyna, chinoksalina i 4,4'-bipy. W przypadku pirazyny i chinoksaliny otrzymane kompleksy są bimetaliczne, w których atomy metali połączone są odpowiednią aminą. Użyty do syntezy 4,4'-bipy pozwolił na otrzymanie dwóch odmian polimorficznych kompleksu {[Co{SSi(tBuO)3}2]2(μ-4,4'bipy)}, a także polimeru koordynacyjnego o wzorze...
-
Influence of circuit breaker operation upon transformeros residual flux and inrush current
PublicationPrzedstawiono model i wyniki obliczeń prądu i strumienia magnetycznego w układzie zawierającym transformator trójfazowy i wyłącznik. Opracowano obwodowy model łącznika z łukiem elektrycznym. Model łuku zbudowano w oparciu o jego statyczną charakterystykę prądowo-napięciową z uwzględnieniem uproszczonej charakterystyki dynamicznej. Przeprowadzone symulacje wykazały, że wartość maksymalna prądu włączania transformatora zależy zarówno...
-
Influence of ci rcuit parameters on the procces of current transfer in thehybrid circuit breaker.
PublicationW artykule przedstawiono działanie hybrydowego bezstykowego ogranicznika prądów zwarciowych w oparciu o symulację komputerową oraz porównanie eksperymentu z symulacją komputerową przy pomocy programu MATLAB i PSPICE. Przedstawiono również wady i zalety obliczeń numerycznych przeprowadzonych z zastosowaniem komercyjnych programów na analizę działania łącznika hybrydowego.W analizie uwzględniono model hybrydowego ogranicznika...
-
Current commutation process in a ultra-fast fuse-IGBT hybrid circuit breaker.
PublicationUkład hybrydowy bezpiecznika topikowego i tranzystora IGBT umożliwia bardzo szybkie włączenie do obwodu zwarciowego impedancji ograniczającej wartość prądu. Po eksplozji krótkiego topika bezpiecznika wywołanej narastającym prądem zwarciowym wywołuje w czasie poniżej 2 ms wzrost napięcia na topiku do wartości ok.20 - 25V, po czym prąd jest komutowany do gałęzi z przyrządem półprzewodnikowym typu GTO lub IGBT. Ostateczne wyłączenie...
-
Optymalizacja procedur dyskryminacyjnych w procesie weryfikacji mówców - metodyka doboru wag parametrów = Optimization of discriminative procedures in speaker verification process - a method for selecting parameter weights
PublicationPoddano testowaniu system weryfikacji mówców, działający w sposób zależny od tekstu, oparty na parametrach cepstralnych. Wstępnie przyjęto wagi wyrównane przypisane do zdefiniowanego w ten sposób wektora wag, właściwego dla obranego systemu parametryzacyjnego. Uzyskane wyniki przedstawiono w postaci macierzy pomyłek (''confusion matrix''). Dobór wartości wektora wag odbywał się w oparciu o część treningową bazy danych przy użyciu...
-
Ribosomal intergenic spacer analysis as a tool for monitoring methanogenic archaea changes in an anaerobic digester
PublicationThe applicability of a newly-designed PCR primer pair in examination of methanogenic Archaea in a digester treating plant biomass was evaluated by Ribosmal Intergenic Spacer Analysis (RISA). To find a suitable approach, three variants of RISA were tested: (1) standard, polyacrylamide gel-based, (2) automated, utilized capillary electrophoresis (GA-ARISA), and (3) automated microfluidics-based (MF-ARISA). All three techniques yielded...
-
MODALITY corpus - SPEAKER 10 - SEQUENCE S1
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 10 - COMMANDS C1
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
Calculations of notch stress factor of a thin-walled spreader bracket fillet weld with the use of a local stress approach
PublicationPresence of geometric notches in welded joints causes concentration of strains and stresses, therefore reducing fatigue strength of such joints. This article presents an analysis of stress concentrations in a fillet weld of a spreader mounting bracket on a small sailing yacht. The aim of this article is to direct the attention of designers, manufacturers and regulatory bodies to issues of fatigue cracks that form in brackets fastening...
-
Creating new voices using normalizing flows
PublicationCreating realistic and natural-sounding synthetic speech remains a big challenge for voice identities unseen during training. As there is growing interest in synthesizing voices of new speakers, here we investigate the ability of normalizing flows in text-to-speech (TTS) and voice conversion (VC) modes to extrapolate from speakers observed during training to create unseen speaker identities. Firstly, we create an approach for TTS...
-
Badanie rozkładów parametrów sygnału mowy w zastosowaniach do prognozowania prawdopodobieństwa popełnienia błędów w systemach identyfikacji mówców = Examining distribution of speech signal parameters for the prognosis of error probability in speaker verification systems
PublicationPrzedmiotem pracy jest system identyfikacji mówców w sposób zależny od tekstu ("text dependent''). Dokonano analizy wielu różnych wypowiedzi kilkudziesięciu mówców. Zastosowana metoda parametryzacji to metoda oparta na wynikach analizy cepstralnej sygnału mowy. Zdefiniowane zostały nowe parametry skojarzone z elementarnymi zdarzeniami w procesie weryfikacji mówców. Na tej podstawie dokonano estymacji funkcji gęstości prawdopodobieństwa...
-
Andrzej Czyżewski prof. dr hab. inż.
PeopleProf. zw. dr hab. inż. Andrzej Czyżewski jest absolwentem Wydziału Elektroniki PG (studia magisterskie ukończył w 1982 r.). Pracę doktorską na temat związany z dźwiękiem cyfrowym obronił z wyróżnieniem na Wydziale Elektroniki PG w roku 1987. W 1992 r. przedstawił rozprawę habilitacyjną pt.: „Cyfrowe operacje na sygnałach fonicznych”. Jego kolokwium habilitacyjne zostało przyjęte jednomyślnie w czerwcu 1992 r. w Akademii Górniczo-Hutniczej...
-
ALOFON corpus
Open Research DataThe ALOFON corpus is one of the multimodal database of word recordings in English, available at http://www.modality-corpus.org/. The ALOFON corpus is oriented towards the recording of the speech equivalence variants. For this purpose, a total of 7 people who are or speak English with native speaker fluency and a variety of Standard Southern British...
-
MODALITY corpus - SPEAKER 35 - COMMANDS C1
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 21 - SEQUENCE S6
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 21 - COMMANDS C5
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 21 - SEQUENCE S4
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 01 - SEQUENCE S2
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 39 - COMMANDS C1
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 01 - SEQUENCE S3
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 01 - COMMANDS C3
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 21 - SEQUENCE S2
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 33 - SEQUENCE S1
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...
-
MODALITY corpus - SPEAKER 01 - COMMANDS C2
Open Research DataThe MODALITY corpus is one of the multimodal database of word recordings in English. It consists of over 30 hours of multimodal recordings. The database contains high-resolution, high-framerate stereoscopic video streams and audio signals obtained from a microphone array and a laptop microphone. The corpus can be employed to develop an AVSR system,...