Filters
total: 408
filtered: 213
Search results for: SPEAKER AUTHENTICATION
-
Improving the quality of speech in the conditions of noise and interference
PublicationThe aim of the work is to present a method of intelligent modification of the speech signal with speech features expressed in noise, based on the Lombard effect. The recordings utilized sets of words and sentences as well as disturbing signals, i.e., pink noise and the so-called babble speech. Noise signal, calibrated to various levels at the speaker's ears, was played over two loudspeakers located 2 m away from the speaker. In...
-
Visual perception of vowels from static and dynamic cues
PublicationThe purpose of the study was to analyse human identification of Polish vowels from static and dynamic durationally slowed visual cues. A total of 152 participants identified 6 Polish vowels produced by 4 speakers from static (still images) and dynamic (videos) cues. The results show that 59% of static vowels and 63% of dynamic vowels were successfully identified. There was a strong confusion between vowels within front, central,...
-
Audio Feature Analysis for Precise Vocalic Segments Classification in English
PublicationAn approach to identifying the most meaningful Mel-Frequency Cepstral Coefficients representing selected allophones and vocalic segments for their classification is presented in the paper. For this purpose, experiments were carried out using algorithms such as Principal Component Analysis, Feature Importance, and Recursive Parameter Elimination. The data used were recordings made within the ALOFON corpus containing audio signal...
-
Examining Influence of Distance to Microphone on Accuracy of Speech Recognition
PublicationThe problem of controlling a machine by the distant-talking speaker without a necessity of handheld or body-worn equipment usage is considered. A laboratory setup is introduced for examination of performance of the developed automatic speech recognition system fed by direct and by distant speech acquired by microphones placed at three different distances from the speaker (0.5 m to 1.5 m). For feature extraction from the voice signal...
-
Machine Learning Applied to Aspirated and Non-Aspirated Allophone Classification—An Approach Based on Audio "Fingerprinting"
PublicationThe purpose of this study is to involve both Convolutional Neural Networks and a typical learning algorithm in the allophone classification process. A list of words including aspirated and non-aspirated allophones pronounced by native and non-native English speakers is recorded and then edited and analyzed. Allophones extracted from English speakers’ recordings are presented in the form of two-dimensional spectrogram images and...
-
The Transmission Protocol of Sensor Ad Hoc Networks
PublicationThis paper presents a secure protocol for a radio Ad Hoc sensor network. This network uses the TDMA multiple access method. The transmission rate on the radio channel is 57.6 kbps. The paper presents the construction of frames, types of packets and procedures for the authentication, assignment of time slots available to the node, releasing assigned slots and slots assignment conflict detection.
-
The secure transmission protocol of sensor Ad Hoc network
PublicationThe paper presents a secure protocol of radio Ad Hoc sensor network. This network operates based on TDMA multiple access method. Transmission rate on the radio channel is 57.6 kbps. The paper presents the construction of frames, types of packets and procedures for the authentication, assignment of time slots available to the node, releasing assigned slots and slots assignment conflict detection.
-
Biometryczna kontrola dostępu
PublicationOpisano szczegółowo algorytm detekcji oraz identyfikacji człowieka na podstawie punktów nodalnych twarzy. Zdefiniowano pojęcia: biometria, proces pomiaru biometrycznego, metody biometrycznej identyfikacji oraz kontrola dostępu. Przedstawiono opis opracowanego systemu biometrycznej identyfikacji wykorzystującego sztuczne sieci neuronowe. Podano wyniki badań oraz przeprowadzono ich wnikliwą dyskusję.Biometrics is the study of automated...
-
Visual Lip Contour Detection for the Purpose of Speech Recognition
PublicationA method for visual detection of lip contours in frontal recordings of speakers is described and evaluated. The purpose of the method is to facilitate speech recognition with visual features extracted from a mouth region. Different Active Appearance Models are employed for finding lips in video frames and for lip shape and texture statistical description. Search initialization procedure is proposed and error measure values are...
-
Uwierzytelnienie i autoryzacja w systemie STRADAR
PublicationPrzedstawiono rozwiązanie serwera uwierzytelnienia i autoryzacji (AA) w rozproszonym systemie STRADAR, udostępniającym funkcjonalności dla prowadzenia działań operacyjnych Morskiego Oddziału Straży Granicznej. System umożliwia prezentację na stanowisku wizualizacji zdarzeń (SWZ) bieżącej i archiwalnej sytuacji na mapie (AIS, radary), obrazu z kamer, zdjęć, notatek, rozmów telefonicznych oraz plików i wiadomości tekstowych (SMS)...
-
Evaluation of aspiration problems in L2 English pronunciation employing machine learning
PublicationThe approach proposed in this study includes methods specifically dedicated to the detection of allophonic variation in English. This study aims to find an efficient method for automatic evaluation of aspiration in the case of Polish second-language (L2) English speakers’ pronunciation when whole words are analyzed instead of particular allophones extracted from words. Sample words including aspirated and unaspirated allophones...
-
MACHINE LEARNING–BASED ANALYSIS OF ENGLISH LATERAL ALLOPHONES
PublicationAutomatic classification methods, such as artificial neural networks (ANNs), the k-nearest neighbor (kNN) and selforganizing maps (SOMs), are applied to allophone analysis based on recorded speech. A list of 650 words was created for that purpose, containing positionally and/or contextually conditioned allophones. For each word, a group of 16 native and non-native speakers were audio-video recorded, from which seven native speakers’...
-
Analysis of human behavioral patterns
PublicationWidespread usage of Internet and mobile devices entailed growing requirements concerning security which in turn brought about development of biometric methods. However, a specially designed biometric system may infer more about users than just verifying their identity. Proper analysis of users’ characteristics may also tell much about their skills, preferences, feelings. This chapter presents biometric methods applied in several...
-
Facial data registration facility for biometric protection of electronic documents
PublicationIn modern world, information is crucial, and its leakage may lead to serious losses. Documents as the main medium of information must be therefore highly protected. Nowadays, the most common way of protecting data is using passwords, however it seems inconvenient to type complex passwords, when it is needed many times a day. For that reason a significant research has been conducted on biometric authentication...
-
The project IDENT: Multimodal biometric system for bank client identity verification
PublicationBiometric identity verification methods are implemented inside a real banking environment comprising: dynamic handwritten signature verification, face recognition, bank cli-ent voice recognition and hand vein distribution verification. A secure communication system based on an intra-bank client-server architecture was designed for this purpose. Hitherto achieved progress within the project is reported in this paper with a focus...
-
Novel 5.1 Downmix Algorithm with Improved Dialogue Intelligibility
PublicationA new algorithm for 5.1 to stereo downmix is introduced, which addresses the problem of dialogue intelligibility. The algorithm utilizes proposed signal processing algorithms to enhance the intelligibility of movie dialogues, especially in difficult listening conditions or in compromised speaker setup. To account for the latter, a playback configuration utilizing a portable device, i.e. an ultrabook, is examined. The experiments...
-
Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech
PublicationWe propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced...
-
Database of speech and facial expressions recorded with optimized face motion capture settings
PublicationThe broad objective of the present research is the analysis of spoken English employing a multiplicity of modalities. An important stage of this process, discussed in the paper, is creating a database of speech accompanied with facial expressions. Recordings of speakers were made using an advanced system for capturing facial muscle motion. A brief historical outline, current applications, limitations and the ways of capturing face...
-
Auto adaptation of mobile device characteristics to various acoustic conditions
PublicationThe proposed methodology of auto adaptation of the mobile device characteristics to various acoustic conditions is presented in the paper. The first goal of this study was to determine the parameters of the acoustic path of the mobile device, for both transmitting (speaker) and receiver (microphone). Results of the measurement of characteristics of mobile devices were presented. Information about characteristics of individual parts...
-
Sensors integration in the smart home environment - a proposal to solve the problem with user identification
PublicationIn this preliminary study we, investigate the possibility of user recognition techniques suitable on smart home devices like chairs, beds, aiming for low–power, high accuracy and quick response time. We propose the two well know technique: voice speaker recognition and accelerometer signal from device mounted on the chair, and the third one optical system basing on IR LED transmitter/receiver circuit. The preliminary results proved...
-
Multimedia industrial and medical applications supported by machine learning
PublicationThis article outlines a keynote paper presented at the Intelligent DecisionTechnologies conference providing a part of the KES Multi-theme Conference “Smart Digital Futures” organized in Rome on June 14–16, 2023. It briefly discusses projects related to traffic control using developed intelligent traffic signs and diagnosing the health of wind turbine mechanisms and multimodal biometric authentication for banking branches to provide...
-
Implementation of power transformer controlled switching algorithm
PublicationThe article presents two new algorithms of controlled switching the power transformer. The main aim of the paper is to obtain formulas that determine the moments of closing of the circuit breaker poles. The study contains projects of control systems for both algorithms. Mathematical formulas for the time instants of the breaker poles closing were developed on the basis of electric circuit theory and magnetic circuit theory. The...
-
Texture Features for the Detection of Playback Attacks: Towards a Robust Solution
PublicationThis paper describes the new version of a method that is capable of protecting automatic speaker verification (ASV) systems from playback attacks. The presented approach uses computer vision techniques, such as the texture feature extraction based on Local Ternary Patterns (LTP), to identify spoofed recordings. Our goal is to make the algorithm independent from the contents of the training set as much as possible; we look for the...
-
Comparison of Acoustic and Visual Voice Activity Detection for Noisy Speech Recognition
PublicationThe problem of accurate differentiating between the speaker utterance and the noise parts in a speech signal is considered. The influence of utilizing a voice activity detection in speech signals on the accuracy of the automatic speech recognition (ASR) system is presented. The examined methods of voice activity detection are based on acoustic and visual modalities. The problem of detecting the voice activity in clean and noisy...
-
Generalized access control in hierarchical computer network
PublicationThe paper presents the design of the security layer for a distributed system located in the multizone hierarchical computer network. Depending on the zone from which a client’s request comes to the system and the type of the request, it will be either authorized or rejected. There is one common layer for the access to all the business services and interactions between them. Unlike the commonly used RBAC model, this system enforces...
-
A fair distribution scheme for joint fingerprinting and decryption methods= Sprawiedliwy schemat dystrybucji dla metod łącznego osadzania odcisku palca oraz deszyfracji
PublicationThe paper addresses the fairness of the security provided by digital fingerprinting methods. It was noted that the digital fingerprinting techniques are designed primarily to protect service providers against the actions of malicious users, while honest users remain vulnerable to acts of malicious providers. The paper describes the customer's rights problem and the unbinding problem, which also apply to joint fingerprinting and...
-
Biometric identity verification
PublicationThis chapter discusses methods which are capable of protecting automatic speaker verification systems (ASV) from playback attacks. Additionally, it presents a new approach, which uses computer vision techniques, such as the texture feature extraction based on Local Ternary Patterns (LTP), to identify spoofed recordings. We show that in this case training the system with large amounts of spectrogram patches may be difficult, and...
-
Building Knowledge for the Purpose of Lip Speech Identification
PublicationConsecutive stages of building knowledge for automatic lip speech identification are shown in this study. The main objective is to prepare audio-visual material for phonetic analysis and transcription. First, approximately 260 sentences of natural English were prepared taking into account the frequencies of occurrence of all English phonemes. Five native speakers from different countries read the selected sentences in front of...
-
Characterization of herbal teas containing lime flowers – Tiliae flos by HPTLC method with chemometric analysis
PublicationLinden trees are a source of food products called lime flowers (Tiliae flos), traditionally used in the form of infusion for the treatment of feverish colds and coughs. Lime flowers should include flowers of Tilia cordata Mill, T.x europaea L., and T. platyphyllos Scop. or a mixture of these. The aim of current research was to establish a fast, sensitive HPTLC (high-performance thin-layer chromatography) method that would allow...
-
Performance analysis of untraceability protocols for mobile agents using an adaptable framework
PublicationArtykuł przedstawia środowisko oceny wydajności protokołów ochrony przed tropieniem agentów mobilnych oraz wyniki analiz przeprowadzonych za jego pomocą. Chociaż środowisko projektowano i implementowano z myślą o ewaluacji zaproponowanych przez nas protokołów ochrony przed tropieniem, w trakcie badań okazało się, że może ono zostać również wykorzystane do badań całej klasy protokołów bezpieczeństwa dla agentów mobilnych. Chodzi...
-
Detection of apple in orange juice using ultra-fast gas chromatography
PublicationThe determination of authenticity is an increasingly important issue for food quality and safety. The use of an electronic nose based on ultra-fast gas chromatography technique ensures rapid analysis of the volatile compounds from food products. Due to the fact that this technique enables chemical profiling of agricultural products, it can be an effective tool for authentication when combined with chemometrics. In this article...
-
Playback Attack Detection: The Search for the Ultimate Set of Antispoof Features
PublicationAutomatic speaker verification systems are vulnerable to several kinds of spoofing attacks. Some of them can be quite simple – for example, the playback of an eavesdropped recording does not require any specialized equipment nor knowledge, but still may pose a serious threat for a biometric identification module built into an e-banking application. In this paper we follow the recent approach and convert recordings to images, assuming...
-
Vocalic Segments Classification Assisted by Mouth Motion Capture
PublicationVisual features convey important information for automatic speech recognition (ASR), especially in noisy environment. The purpose of this study is to evaluate to what extent visual data (i.e. lip reading) can enhance recognition accuracy in the multi-modal approach. For that purpose motion capture markers were placed on speakers' faces to obtain lips tracking data during speaking. Different parameterizations strategies were tested...
-
A Study of Cross-Linguistic Speech Emotion Recognition Based on 2D Feature Spaces
PublicationIn this research, a study of cross-linguistic speech emotion recognition is performed. For this purpose, emotional data of different languages (English, Lithuanian, German, Spanish, Serbian, and Polish) are collected, resulting in a cross-linguistic speech emotion dataset with the size of more than 10.000 emotional utterances. Despite the bi-modal character of the databases gathered, our focus is on the acoustic representation...
-
Evaluation of respiration rate and pattern using a portable thermal camera
PublicationThe goal of this paper was to analyze the accuracy of the proposed method for the evaluation of respiration rate and respiration rhythm patterns (e.g. inspiration slope) using the portable and mobile thermal camera module that could be a part of smart glasses. Parameters were analyzed for 12 volunteers in two experiments, when subjects speak and do not speak. The pressure, chest belt was used as a reference measurement method....
-
Synthesis and antiproliferative activity of conjugates of adenosine with muramyl dipeptide and nor-muramyl dipeptide derivatives
PublicationWe synthesized a series of MDP(D,D) and nor-MDP(D,D) derivatives conjugated with adenosine through a spacer as potential immunosuppressants. New conjugates were evaluated on two leukemia cell lines (Jurkat and L1210) and PBMC from healthy donors.
-
Novel analytical method for detection of orange juice adulteration based on ultra-fast gas chromatography
PublicationThe food authenticity assessment is an increasingly important issue in food quality and safety. The application of an electronic nose based on ultra-fast gas chromatography technique enables rapid analysis of the volatile compounds from food samples. Due to the fact that this technique provides chemical profiling of natural products, it can be a powerful tool for authentication in combination with chemometrics. In this article,...
-
Non-volatile molecular composition and discrimination of single grape white of chardonnay, riesling, sauvignon blanc and silvaner using untargeted GC–MS analysis
PublicationThis study developed and applied a GC–MS method aiming at molecular fingerprinting of 120 commercial single grape white wines (Chardonnay, Riesling, Sauvignon Blanc and Silvaner) for possible authentication according to grape variety. The method allowed detection of 372 peaks and tentative identification of 146 metabolites including alcohols, organic acids, esters, amino acids and sugars. The grape variety effect explained 8.3%...
-
Modelling of Ship’s Heeling and Rolling for the Purpose of Gantry Control Improvement in the Course of Cargo Handling Operations in Sea Ports
PublicationThe paper presents two proposals of models of interaction between a ship and cargo being loaded or discharged by a gantry in port, in terms of heeling and rolling of the vessel. The main purpose of such modelling is the need for improvement of gantry control with regard to faster operations thanks to more accurate estimation of level and moment of cargo release from a gantry hook or spreader. The study may be the contribution to...
-
Just look at to open it up: A biometric verification facility for password autofill to protect electronic documents
PublicationElectronic documents constitute specific units of information, and protecting them against unauthorized access is a challenging task. This is because a password protected document may be stolen from its host computer or intercepted while on transfer and exposed to unlimited offline attacks. The key issue is, therefore, making document passwords hard to crack. We propose to augment a common text password authentication interface...
-
Areas of Updraft Air Motion in an Idealised Weather Research and Forecasting Model Simulation of Atmospheric Boundary Layer Response to Different Floe Size Distributions
PublicationPresented dataset is part of a numerical modelling study focusing on the analysis of the influence of sea ice floe size distribution (FSD) on the horizontal and vertical structure of convection in the atmosphere. The total area and spatial arrangement of the up-drafts indicates that the FSD affects the total moisture content and the values of area averaged turbulent fluxes in the model domain. In fact, while convective updrafts...
-
Independence in uniform linear triangle-free hypergraphs
PublicationThe independence number a(H) of a hypergraph H is the maximum cardinality of a set of vertices of H that does not contain an edge of H. Generalizing Shearer’s classical lower bound on the independence number of triangle-free graphs Shearer (1991), and considerably improving recent results of Li and Zang (2006) and Chishti et al. (2014), we show a new lower bound for a(H) for an r-uniform linear triangle-free hypergraph H with r>=2.
-
Next generation automatic IP configuration deployment issues
PublicationAlthough Dynamic Host Configuration Protocol for IPv6 (DHCPv6) protocol was defined in 2003, it was designed as a framework rather than a complete solution to the automatic configuration in IPv6 networks. There are still some unsolved problems and new options yet to be defined. One example of such case is Fully Qualified Domain Name (FQDN) option, which final version has been published in late 2007. It describes DHCPv6 client...
-
Comparison of an Electronic Nose Based on Ultrafast Gas Chromatography, Comprehensive Two-Dimensional Gas Chromatography, and Sensory Evaluation for an Analysis of Type of Whisky
PublicationWhisky is one of the most popular alcoholic beverages. There are many types of whisky, for example, Scotch, Irish, and American whisky (called bourbon). The whisky market is highly diversified, and, because of this, it is important to have a method which would enable rapid quality evaluation and authentication of the type of whisky. The aim of this work was to compare 3 methods: an electronic nose based on the technology of ultrafast...
-
Digital Public Service Innovation: Framework Proposal
PublicationThis paper proposes the Digital Public Service Innovation Framework that extends the "standard" provision of digital public services according to the emerging, enhanced, transactional and connected stages underpinning the United Nations Global e-Government Survey, with seven example "innovations" in digital public service delivery -- transparent, participatory, anticipatory, personalized, co-created, context-aware and context-smart....
-
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
PublicationThis paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically de...
-
A comparative study of English viseme recognition methods and algorithms
PublicationAn elementary visual unit – the viseme is concerned in the paper in the context of preparing the feature vector as a main visual input component of Audio-Visual Speech Recognition systems. The aim of the presented research is a review of various approaches to the problem, the implementation of algorithms proposed in the literature and a comparative research on their effectiveness. In the course of the study an optimal feature vector construction...
-
A comparative study of English viseme recognition methods and algorithm
PublicationAn elementary visual unit – the viseme is concerned in the paper in the context of preparing the feature vector as a main visual input component of Audio-Visual Speech Recognition systems. The aim of the presented research is a review of various approaches to the problem, the implementation of algorithms proposed in the literature and a comparative research on their effectiveness. In the course of the study an optimal feature vector...
-
Necessary and Sufficient Condition for State-Independent Contextual Measurement Scenarios
PublicationThe problem of identifying measurement scenarios capable of revealing state-independent contextuality in a given Hilbert space dimension is considered. We begin by showing that for any given dimension d and any measurement scenario consisting of projective measurements, (i) the measure of contextuality of a quantum state is entirely determined by its spectrum, so that pure and maximally mixed states represent the two extremes...
-
Material for Automatic Phonetic Transcription of Speech Recorded in Various Conditions
PublicationAutomatic speech recognition (ASR) is under constant development, especially in cases when speech is casually produced or it is acquired in various environment conditions, or in the presence of background noise. Phonetic transcription is an important step in the process of full speech recognition and is discussed in the presented work as the main focus in this process. ASR is widely implemented in mobile devices technology, but...