Dissertations / Theses on the topic 'Voice biometrics'

This thesis describes research into effective voice biometrics (speaker recognition) under mismatched noise conditions. Over the last two decades, this class of biometrics has been the subject of considerable research due to its various applications in such areas as telephone banking, remote access control and surveillance. One of the main challenges associated with the deployment of voice biometrics in practice is that of undesired variations in speech characteristics caused by environmental noise. Such variations can in turn lead to a mismatch between the corresponding test and reference material from the same speaker. This is found to adversely affect the performance of speaker recognition in terms of accuracy. To address the above problem, a novel approach is introduced and investigated. The proposed method is based on minimising the noise mismatch between reference speaker models and the given test utterance, and involves a new form of Test-Normalisation (T-Norm) for further enhancing matching scores under the aforementioned adverse operating conditions. Through experimental investigations, based on the two main classes of speaker recognition (i.e. verification/ open-set identification), it is shown that the proposed approach can significantly improve the performance accuracy under mismatched noise conditions. In order to further improve the recognition accuracy in severe mismatch conditions, an approach to enhancing the above stated method is proposed. This, which involves providing a closer adjustment of the reference speaker models to the noise condition in the test utterance, is shown to considerably increase the accuracy in extreme cases of noisy test data. Moreover, to tackle the computational burden associated with the use of the enhanced approach with open-set identification, an efficient algorithm for its realisation in this context is introduced and evaluated. The thesis presents a detailed description of the research undertaken, describes the experimental investigations and provides a thorough analysis of the outcomes.

Deepfake technológia je v poslednej dobe na vzostupe. Vzniká mnoho techník a nástrojov pre tvorbu deepfake médií a začínajú sa používať ako pre nezákonné tak aj pre prospešné činnosti. Nezákonné použitie vedie k výskumu techník pre detekciu deepfake médií a ich neustálemu zlepšovaniu, takisto ako k potrebe vzdelávať širokú verejnosť o nástrahách, ktoré táto technológia prináša. Jedna z málo preskúmaných oblastí škodlivého použitia je používanie deepfake pre oklamanie systémov hlasovej autentifikácie. Názory spoločnosti na vykonateľnosť takýchto útokov sa líšia, no existuje len málo vedeckých dôkazov. Cieľom tejto práce je preskúmať aktuálnu pripravenosť systémov hlasovej biometrie čeliť deepfake nahrávkam. Vykonané experimenty ukazujú, že systémy hlasovej biometrie sú zraniteľné pomocou deepfake nahrávok. Napriek tomu, že skoro všetky verejne dostupné nástroje a modely sú určené pre syntézu anglického jazyka, v tejto práci ukazujem, že syntéza hlasu v akomkoľvek jazyku nie je veľmi náročná. Nakoniec navrhujem riešenie pre zníženie rizika ktoré deepfake nahrávky predstavujú pre systémy hlasovej biometrie, a to používať overenie hlasu závislé na texte, nakoľko som ukázal, že je odolnejšie proti deepfake nahrávkam.

Identity verification systems are an important part of our every day life. A typical example is the Automatic Teller Machine (ATM) which employs a simple identity verification scheme: the user is asked to enter their secret password after inserting their ATM card; if the password matches the one prescribed to the card, the user is allowed access to their bank account. This scheme suffers from a major drawback: only the validity of the combination of a certain possession (the ATM card) and certain knowledge (the password) is verified. The ATM card can be lost or stolen, and the password can be compromised. Thus new verification methods have emerged, where the password has either been replaced by, or used in addition to, biometrics such as the person’s speech, face image or fingerprints. Apart from the ATM example described above, biometrics can be applied to other areas, such as telephone & internet based banking, airline reservations & check-in, as well as forensic work and law enforcement applications. Biometric systems based on face images and/or speech signals have been shown to be quite effective. However, their performance easily degrades in the presence of a mismatch between training and testing conditions. For speech based systems this is usually in the form of channel distortion and/or ambient noise; for face based systems it can be in the form of a change in the illumination direction. A system which uses more than one biometric at the same time is known as a multi-modal verification system; it is often comprised of several modality experts and a decision stage. Since a multi-modal system uses complimentary discriminative information, lower error rates can be achieved; moreover, such a system can also be more robust, since the contribution of the modality affected by environmental conditions can be decreased. This thesis makes several contributions aimed at increasing the robustness of single- and multi-modal verification systems. Some of the major contributions are listed below. The robustness of a speech based system to ambient noise is increased by using Maximum Auto-Correlation Value (MACV) features, which utilize information from the source part of the speech signal. A new facial feature extraction technique is proposed (termed DCT-mod2), which utilizes polynomial coefficients derived from 2D Discrete Cosine Transform (DCT) coefficients of spatially neighbouring blocks. The DCT-mod2 features are shown to be robust to an illumination direction change as well as being over 80 times quicker to compute than 2D Gabor wavelet derived features. The fragility of Principal Component Analysis (PCA) derived features to an illumination direction change is solved by introducing a pre-processing step utilizing the DCT-mod2 feature extraction. We show that the enhanced PCA technique retains all the positive aspects of traditional PCA (that is, robustness to compression artefacts and white Gaussian noise) while also being robust to the illumination direction change. Several new methods, for use in fusion of speech and face information under noisy conditions, are proposed; these include a weight adjustment procedure, which explicitly measures the quality of the speech signal, and a decision stage comprised of a structurally noise resistant piece-wise linear classifier, which attempts to minimize the effects of noisy conditions via structural constraints on the decision boundary.

Identity verification systems are an important part of our every day life. A typical example is the Automatic Teller Machine (ATM) which employs a simple identity verification scheme: the user is asked to enter their secret password after inserting their ATM card; if the password matches the one prescribed to the card, the user is allowed access to their bank account. This scheme suffers from a major drawback: only the validity of the combination of a certain possession (the ATM card) and certain knowledge (the password) is verified. The ATM card can be lost or stolen, and the password can be compromised. Thus new verification methods have emerged, where the password has either been replaced by, or used in addition to, biometrics such as the person’s speech, face image or fingerprints. Apart from the ATM example described above, biometrics can be applied to other areas, such as telephone & internet based banking, airline reservations & check-in, as well as forensic work and law enforcement applications. Biometric systems based on face images and/or speech signals have been shown to be quite effective. However, their performance easily degrades in the presence of a mismatch between training and testing conditions. For speech based systems this is usually in the form of channel distortion and/or ambient noise; for face based systems it can be in the form of a change in the illumination direction. A system which uses more than one biometric at the same time is known as a multi-modal verification system; it is often comprised of several modality experts and a decision stage. Since a multi-modal system uses complimentary discriminative information, lower error rates can be achieved; moreover, such a system can also be more robust, since the contribution of the modality affected by environmental conditions can be decreased. This thesis makes several contributions aimed at increasing the robustness of single- and multi-modal verification systems. Some of the major contributions are listed below. The robustness of a speech based system to ambient noise is increased by using Maximum Auto-Correlation Value (MACV) features, which utilize information from the source part of the speech signal. A new facial feature extraction technique is proposed (termed DCT-mod2), which utilizes polynomial coefficients derived from 2D Discrete Cosine Transform (DCT) coefficients of spatially neighbouring blocks. The DCT-mod2 features are shown to be robust to an illumination direction change as well as being over 80 times quicker to compute than 2D Gabor wavelet derived features. The fragility of Principal Component Analysis (PCA) derived features to an illumination direction change is solved by introducing a pre-processing step utilizing the DCT-mod2 feature extraction. We show that the enhanced PCA technique retains all the positive aspects of traditional PCA (that is, robustness to compression artefacts and white Gaussian noise) while also being robust to the illumination direction change. Several new methods, for use in fusion of speech and face information under noisy conditions, are proposed; these include a weight adjustment procedure, which explicitly measures the quality of the speech signal, and a decision stage comprised of a structurally noise resistant piece-wise linear classifier, which attempts to minimize the effects of noisy conditions via structural constraints on the decision boundary.
Thesis (PhD Doctorate)
Doctor of Philosophy (PhD)
School of Microelectronic Engineering
Full Text

Our purpose with this thesis was to find biometric methods that can be used in access control of mobile access. The access control has two parts. Firstly, to validate the identity of the caller and, secondly, to ensure the validated user is not changed during the session that follows. Any solution to the access control problem is not available today, which means that anyone can get access to the mobile phone and the Internet. Therefore we have researched after a solution that can solve this problem but also on how to secure that no one else can take over an already validated session. We began to search for biometric methods that are available today to find them that would be best suited together with a mobile phone. After we had read information about them we did choose three methods for further investigation. These methods were Fingerprint Recognition, Iris Scan and Speaker Verification. Iris Scan is the method that is best suited to solve the authentication problem. The reasons for this are many. One of them is the uniqueness and stability of the iris, not even identical twins or the pair of the same individual has the same iris minutiae. The iris is also very protected behind eyelids, cornea and the aqueous humor and therefore difficult to damage. When it comes to the method itself, is it one of the most secure methods available today. One of the reasons for this is that the equal error rate is better than one in a million. However, this rate can be even better. It all depends on the Hamming Distance, which is a value that show how different the saved and temporarily template are, and what it is set to. To solve our session authentication, which was to make sure that no one else could take over a connected mobile phone, a sensor plate is the answer. This sensor will be able to sense for touch, heat and pulse. These three sensor measurements will together secure a validated session since the mobile phone will disconnect if the sensor looses its sensor data. There are, however, technological and other challenges to be solved before our proposed solutions will become viable. We address some of these issues in our thesis.

This thesis introduces readers to the basic types of the text and information inputs and processing to the computer. Thesis also includes historical contexts, current trends and future perspective of computer data input technologies and their use in practice. The first part of the thesis is a summary of a particular forms of entering and processing of the text data and information. The following part presents technological trends on the market concentrated on the automatic speech recognition systems along with the possibilities of their application in the business sphere. The rest of the thesis consists of a survey between Czech IT companies and based on it's results comes a suggestion of which technologies should be used as a part of the information systems.

La segmentation et le regroupement en locuteurs (SRL) impliquent la détection des locuteurs dans un flux audio et les intervalles pendant lesquels chaque locuteur est actif, c'est-à-dire la détermination de ‘qui parle quand’. La première partie des travaux présentés dans cette thèse exploite une approche de modélisation du locuteur utilisant des clés binaires (BKs) comme solution à la SRL. La modélisation BK est efficace et fonctionne sans données d'entraînement externes, car elle utilise uniquement des données de test. Les contributions présentées incluent l'extraction des BKs basée sur l'analyse spectrale multi-résolution, la détection explicite des changements de locuteurs utilisant les BKs, ainsi que les techniques de fusion SRL qui combinent les avantages des BKs et des solutions basées sur un apprentissage approfondi. La tâche de la SRL est étroitement liée à celle de la reconnaissance ou de la détection du locuteur, qui consiste à comparer deux segments de parole et à déterminer s'ils ont été prononcés par le même locuteur ou non. Même si de nombreuses applications pratiques nécessitent leur combinaison, les deux tâches sont traditionnellement exécutées indépendamment l'une de l'autre. La deuxième partie de cette thèse porte sur une application où les solutions de SRL et de reconnaissance des locuteurs sont réunies. La nouvelle tâche, appelée détection de locuteurs à faible latence, consiste à détecter rapidement les locuteurs connus dans des flux audio à locuteurs multiples. Il s'agit de repenser la SRL en ligne et la manière dont les sous-systèmes de SRL et de détection devraient être combinés au mieux
Speaker diarization (SD) involves the detection of speakers within an audio stream and the intervals during which each speaker is active, i.e. the determination of ‘who spoken when’. The first part of the work presented in this thesis exploits an approach to speaker modelling involving binary keys (BKs) as a solution to SD. BK modelling is efficient and operates without external training data, as it operates using test data alone. The presented contributions include the extraction of BKs based on multi-resolution spectral analysis, the explicit detection of speaker changes using BKs, as well as SD fusion techniques that combine the benefits of both BK and deep learning based solutions. The SD task is closely linked to that of speaker recognition or detection, which involves the comparison of two speech segments and the determination of whether or not they were uttered by the same speaker. Even if many practical applications require their combination, the two tasks are traditionally tackled independently from each other. The second part of this thesis considers an application where SD and speaker recognition solutions are brought together. The new task, coined low latency speaker spotting (LLSS), involves the rapid detection of known speakers within multi-speaker audio streams. It involves the re-thinking of online diarization and the manner by which diarization and detection sub-systems should best be combined

Notizie riguardanti scandali relativi al utilizzo inappropriato di contrassegni per disabili sono all’ordine del giorno. Situazioni meno popolari dal punto di vista mediatico, ma altrettanto gravi a livello sociale coinvolgono tutti quegli individui che si prodigano a falsificare contrassegni oppure ad utilizzarli anche in mancanza del disabile, eventualmente anche successivamente al decesso del medesimo. Tutto questo va inevitabilmente a discapito di tutti coloro che hanno reale diritto e necessità di usufruire delle agevolazioni. Lo scopo di questa tesi è quindi quello di illustrare un possibile sistema per contrastare e possibilmente debellare questo malcostume diffusissimo in Italia. La proposta è quella di dematerializzare il pass cartaceo sostituendolo con un equiva- lente elettronico, temporaneo e associato non più ad una targa, ma all’individuo stesso. Per farlo si ricorrerà all’uso di tecniche di autenticazione attraverso sistemi biometrici, quali il riconoscimento facciale, vocale, di espressioni facciali e gestures.

La segmentation et le regroupement en locuteurs (SRL) impliquent la détection des locuteurs dans un flux audio et les intervalles pendant lesquels chaque locuteur est actif, c'est-à-dire la détermination de ‘qui parle quand’. La première partie des travaux présentés dans cette thèse exploite une approche de modélisation du locuteur utilisant des clés binaires (BKs) comme solution à la SRL. La modélisation BK est efficace et fonctionne sans données d'entraînement externes, car elle utilise uniquement des données de test. Les contributions présentées incluent l'extraction des BKs basée sur l'analyse spectrale multi-résolution, la détection explicite des changements de locuteurs utilisant les BKs, ainsi que les techniques de fusion SRL qui combinent les avantages des BKs et des solutions basées sur un apprentissage approfondi. La tâche de la SRL est étroitement liée à celle de la reconnaissance ou de la détection du locuteur, qui consiste à comparer deux segments de parole et à déterminer s'ils ont été prononcés par le même locuteur ou non. Même si de nombreuses applications pratiques nécessitent leur combinaison, les deux tâches sont traditionnellement exécutées indépendamment l'une de l'autre. La deuxième partie de cette thèse porte sur une application où les solutions de SRL et de reconnaissance des locuteurs sont réunies. La nouvelle tâche, appelée détection de locuteurs à faible latence, consiste à détecter rapidement les locuteurs connus dans des flux audio à locuteurs multiples. Il s'agit de repenser la SRL en ligne et la manière dont les sous-systèmes de SRL et de détection devraient être combinés au mieux
Speaker diarization (SD) involves the detection of speakers within an audio stream and the intervals during which each speaker is active, i.e. the determination of ‘who spoken when’. The first part of the work presented in this thesis exploits an approach to speaker modelling involving binary keys (BKs) as a solution to SD. BK modelling is efficient and operates without external training data, as it operates using test data alone. The presented contributions include the extraction of BKs based on multi-resolution spectral analysis, the explicit detection of speaker changes using BKs, as well as SD fusion techniques that combine the benefits of both BK and deep learning based solutions. The SD task is closely linked to that of speaker recognition or detection, which involves the comparison of two speech segments and the determination of whether or not they were uttered by the same speaker. Even if many practical applications require their combination, the two tasks are traditionally tackled independently from each other. The second part of this thesis considers an application where SD and speaker recognition solutions are brought together. The new task, coined low latency speaker spotting (LLSS), involves the rapid detection of known speakers within multi-speaker audio streams. It involves the re-thinking of online diarization and the manner by which diarization and detection sub-systems should best be combined

This work deals with the text-dependent speaker recognition in systems, where just a few training samples exist. For the purpose of this recognition, the voice imprint based on different features (e.g. MFCC, PLP, ACW etc.) is proposed. At the beginning, there is described the way, how the speech signal is produced. Some speech characteristics important for speaker recognition are also mentioned. The next part of work deals with the speech signal analysis. There is mentioned the preprocessing and also the feature extraction methods. The following part describes the process of speaker recognition and mentions the evaluation of the used methods: speaker identification and verification. Last theoretically based part of work deals with the classifiers which are suitable for the text-dependent recognition. The classifiers based on fractional distances, dynamic time warping, dispersion matching and vector quantization are mentioned. This work continues by design and realization of system, which evaluates all described classifiers for voice imprint based on different features.

Вирішення проблеми захисту корпоративних даних в ХХІ столітті вийшло за рамки фізичної взаємодії з працівниками, у зв’язку з переходом шуканої інформації в комп’ютерний формат. Дана особливість сформувала потребу у розробці та імплементації нових механізмів захисту корпоративних даних. Запропонована система аутентифікації користувачів комп’ютерних систем, розроблена на основі технологій нейронних мереж, надає можливість ідентифікації користувачів на основі індивідуальних антропометричних візуальних та голосових показників суб’єкта, з метою запобігання викраденню корпоративних даних, та ідентифікації злочинних суб’єктів. Об’єктом дослідження є трансформація антропометричних показників в комп’ютерну форму. Предметом дослідження є механізми розпізнавання образів. Метою роботи є покращення можливостей методів біометричної ідентифікації суб’єктів шляхом розробки нової архітектури на базі нейронних мереж. Методи дослідження. Порівняння існуючих алгоритмів за критеріями точності, швидкодії, ресурсних затрат, надійності, з метою імплементації та подальшої модифікації в системі корпоративного контролю. Наукова новизна полягає у розробці нового механізму ідентифікації суб’єктів що поєднує у собі алгоритми голосової та візуальної ідентифікації суб’єктів. Практична цінність полягає у можливості застосування даної системи в корпоративних умовах з метою запобігання витоку даних та ідентифікації злочинних суб’єктів. Низька ресурсозатратність сприяє застосуванню розробленого алгоритму в високонавантажених системах. Структура та обсяг роботи. Магістерська дисертація складається з вступу, чотирьох розділів, висновків та додатків. У вступі аналізується проблема захисту корпоративних даних. Обгрунтовується перспективність застосування механізмів біометричної голосової та візуальної ідентифікації суб’єктів для її вирішення. Досліджуються алгоритми біометричної ідентифікації. У першому розділі описуються існуючі алгоритми розпізнавання візуальних та голосових образів. У другому розділі досліджується доцільність застосування існуючих алгоритмів голосової та візуальної біометричної ідентифікації, аналізуються та порівнюються існуючі архітектури розпізнавання образів. У третьому розділі наводиться процес розробки алгоритмів візуальної та голосової біометричної ідентифікації користувачів У четвертому розділі наводяться характеристики розробленої КС, результати тестування, відбувається дослідження системи на різних наборах даних, та її модифікація з метою досягнення поставленої точності. У висновках стисло наводяться результати досліджень та розробки.
Topic relevance The solution to the problem of corporate data protection in the XXI century has gone beyond the physical interaction with employees, due to the transition of the required information into a computer format. This feature has formed the need to develop and implement new mechanisms for corporate data protection. The proposed system of authentication of computer system users, developed on the basis of neural network technologies, provides the possibility of user identification on the basis of individual anthropometric visual and voice indicators of the subject, in order to prevent theft of corporate data and identification of criminal entities. The object of study is the transformation of anthropometric indicators into a computer form. The subject of study is the mechanisms of pattern recognition. The goal of this work is to improve the capabilities of biometric identification methods of subjects by developing a new architecture based on neural networks. Study methods. Comparison of existing algorithms on the criteria of accuracy, speed, resource costs, reliability, in order to implement and further modify the corporate control system. The scientific novelty is the development of a new mechanism for identifying subjects that combines algorithms for voice and visual identification of subjects. The practical value lies in the possibility of using this system in a corporate environment in order to prevent data leakage and identification of criminal entities. Low resource consumption contributes to the application of the developed algorithm in highly loaded systems. Structure and scope of work. The master's dissertation consists of an introduction, four chapters, conclusions and appendices. The introduction analyzes the problem of corporate data protection. The prospects of using the mechanisms of biometric voice and visual identification of subjects for its solution are substantiated. Biometric identification algorithms are investigated. The first section describes the existing algorithms for recognizing visual and voice images. The second section investigates the feasibility of using existing algorithms for voice and visual biometric identification, analyzes and compares existing image recognition architectures. The third section describes the process of developing algorithms for visual and voice biometric user identification The fourth section presents the characteristics of the developed COP, the test results, the system is studied on different data sets, and its modification in order to achieve the specified accuracy. The conclusions summarize the results of research and development.

In a world dominated by smartphones, cloud computing, and online accounts, security of personal and corporate data is a critical concern. Voiceprint Vault provides a voice authentication service that can be used in a multitude of applications to secure sensitive data. Voiceprint Vault includes the following high-level features: - Cloud-based voice authentication using trusted signal processing algorithms - Multifactor authentication with use of optional password - Cross-platform compatibility using secure web requests to authenticate - Built-in storage and synching of private user data - Java library to facilitate integration with Android applications The Voiceprint Vault service allows users of an application to create an account, provide a voice sample, and then access the account with a simple spoken phrase. When users access their account, their voice sample is analyzed and compared to their training recordings. This system can be tailored to the needs of a particular user with per-user security options. It provides the convenience of voice access, but also allows for a password to be used for increased security. The Voiceprint Vault service is designed to allow application developers to integrate an existing, tested authentication system into their app rather than creating their own authentication system. The Voiceprint Vault server provides application specific repositories that developers can create to hold all user data, cryptographic information, and voice samples. The user data stored on the Voiceprint Vault server provides built-in synchronization across all connected devices. A reference implementation is provided that demonstrates the use of Voiceprint Vault authentication. The reference implementation is an Android app that uses the voice authentication service to protect access to personal notes, tasks, and dates that are synched across devices. Detailed instructions for integrating Voiceprint Vault into an existing application are also provided with the reference implementation. The accuracy of voiceprint authentication was investigated and optimized for a set of sample users and recordings. The security features and dangers of such a system are described along with recommendations for safe use. The optimal parameters to be used in the voice authentication algorithms are also presented in this report.
text

Tese de doutoramento em Psicologia, (área de especialização em Psicologia Clínica)
Concetualização: A Psicopatologia do Desenvolvimento trouxe uma nova perspetiva na compreensão de como a depressão materna na gravidez pode contribuir para os resultados adversos no desenvolvimento fetal e neonatal. O estudo dos mecanismos subjacentes à transmissão do risco mãe-filho revelou a contribuição de variáveis fetais na explicação das diferenças individuais no desenvolvimento. Objetivos: 1) Estudar os efeitos da depressão materna na gravidez no desenvolvimento fetal e neonatal; 2) Analisar a depressão materna no parto como potencial mediador/moderador da relação entre depressão materna na gravidez e desenvolvimento neonatal; 3) Avaliar a resposta cardíaca fetal à administração de um paradigma de familiaridade-novidade com estímulos auditivos/discursivos; e, 4) Identificar potenciais mecanismos que permitam explicar a relação entre depressão materna na gravidez e desenvolvimento neonatal. Método: Uma amostra de 110 grávidas (no terceiro trimestre de gravidez) foi dividida em dois grupos de acordo com a sua cotação na Edinburgh Postnatal Depression Scale (EPDS: 10, deprimidas; < 10, não-deprimidas). Entre a 33ª e a 37ª semana de gravidez, as participantes contaram uma curta história aos seus fetos, todos os dias. A frequência cardíaca fetal (FCF) foi avaliada à 37ª semana de gestação através de um cardiotocograma computorizado, enquanto uma gravação dos estímulos discursivos (história familiar e história nova) era apresentada próximo do abdómen materno. Medidas da FCF em resposta à estimulação e da biometria fetal foram recolhidas no terceiro trimestre de gestação. Nos primeiros 5 dias após o parto, os recém-nascidos foram avaliados através da Neonatal Behavioral Assessment Scale (NBAS) e do paradigma da ‘Preferencia e habituação pela face/voz da mãe/estranha’; as mães preencheram o EPDS. Resultados: Os fetos de grávidas deprimidas, apresentaram menor perímetro cefálico e abdominal, em comparação com os fetos de grávidas não deprimidas. Recém-nascidos de mães deprimidas, comparativamente com recémnascidos de mães não deprimidas na gravidez, revelaram piores resultados nas subescalas da NBAS (regulação do estado, mudança de estado e habituação); não mostraram preferência visual/auditória pela face/voz da mãe; necessitaram mais apresentações do estímulo face/voz da mãe até se habituarem; e apresentaram maior preferência visual/auditória pela face/voz da estranha após habituação. A depressão no parto não contribuiu para os efeitos da depressão materna na gravidez no desenvolvimento neonatal. Uma maior variabilidade da FCF foi observada durante a apresentação de estímulos discursivos (em oposição ao préteste), bem como na primeira apresentação do estímulo familiar (em oposição ao estímulo novo) e na terceira apresentação do estímulo novo (em oposição à primeira apresentação). Não se observaram diferenças significativas na linha de base da FCF. A variabilidade da FCF mediou a relação entre depressão materna na gravidez e o neurocomportamento do recém-nascido, explicando 11.7% da variância observada. Conclusão: A depressão materna na gravidez é uma condição de risco para o desenvolvimento neonatal, sendo que a sintomatologia depressiva materna nos primeiros dias após o parto não explica os resultados desenvolvimentais do recém-nascido. A variabilidade de FCF surge a explicar a relação entre depressão materna no terceiro trimestre de gestação e desenvolvimento neonatal. Com vista à redução do risco associado à depressão materna justifica-se a implementação de medidas preventivas de saúde materno-fetal, precocemente na gravidez.
Background: Developmental Psychopathology has brought new possibilities for understanding how maternal depression during pregnancy may contribute to adverse foetal and neonatal development. The study of the underlying mechanisms of motherto- child transmission of risk, have shown the contribution of foetal variables in the explanation of the following development. Aims: 1) To study the effect of mother’s depression during pregnancy on foetal and neonatal development; 2) To analyse mother’s depression at childbirth as a potential mecanism in the explanation of the relationship between mother’s depression during pregnancy and neonate development; 3) To evaluate the fetal cardiac response during the administration of a familiaritynovelty paradigm with auditory/discursive stimuli; and 4) To identify potential foetal mediators/moderators of the relationship between mother’s depression during pregnancy and neonatal development. Method: A sample of 110 pregnant women (at the third trimester of pregnancy) was divided in 2 groups according to their scores on the Edinburgh Postnatal Depression Scale (EPDS: 10, depressed; < 10, nondepressed). Between the 33rd and the 37th week of gestation, mothers recited a short nursery rhyme to their fetuses every day. Fetal heart rate (FHR) was assessed at 37 weeks gestation by computerised cardiotocography, while pre-recorded speech stimuli (familiar and novel nursery rhymes) were presented using a loudspeaker held above the maternal abdomen. Measures of FHR in response to stimuli and foetal biometry were collected at the third pregnancy trimester. In the first 5 days after birth, neonatal performance on the Neonatal Behavioral Assessment Scale (NBAS) and in the ‘Preference and habituation to the mother’s face/voice versus stranger’ paradigm was assessed; each mother filled out an EPDS. Results: The foetuses of depressed pregnant women, had an inferior head and abdomen circumference growth, compared to foetuses of non-depressed pregnant women. Neonates of depressed mothers, compared to neonates of non-depressed mothers, achieved lower scores on the NBAS scales (regulation of state, range of state, and habituation); did not show a visual/auditory preference for the mother’s face/voice; required more trials to become habituated; and showed a higher visual/auditory preference for the stranger’s face/voice after habituation. Depression at childbirth does not contribute to the effect of antenatal depression on neonatal development. A significantly higher FHR variability was observed during stimuli presentation (in opposition to pretest), as well as during the first presentation of the familiar stimulus (in opposition to the novel stimulus), and in the third presentation of the novel stimulus (in opposition to its first presentation). No significant changes were observed in baseline FHR. FHR variability mediates the relationship between mother’s depression during pregnancy and neonate neurobehaviour, explaining 11.7% of the variance observed. Conclusion: Mother’s depression during pregnancy is a risk condition for neonates’ development. Depression at the first days after childbirth does not contribute to neonates’ developmental outcomes. FHR variability explaine the relation between mother’s depression at the third pregnancy trimester and neonatal development. In order to reduce the risk associated with maternal depression, the implementation of preventive maternal-fetal health measures, early in pregnancy, is needed.

Роботу присвячено обґрунтуванню методу ідентифікації особи у телекомунікаційній мережі.Розглянуто існуючі методи ідентифікації особи за характеристиками біометричних даних та встановлено, що такі методи вирізняються вищою точністю. Обґрунтовано метод ідентифікаціїособи за голосовим сигналом, який є надійним та дешевим у реалізації.Застосовуючи у такому методі оптимальні способи обробки аудіо сигналів ідентифікація здійснюється з високою достовірністю. В якості інформативних параметрів голосових сигналів запропоновано використати формантні частоти амплітудного спектру голосових сигналів та значення частоти основного тону.
The master's thesis is devoted to solving the actual scientific and practical problem of developing methods of providing information and functional security of wireless infrastructure on the basis of hardware separation of subscribers to increase the level of its protection against security threats of various nature, which consist in the developed theoretical bases, methods, models and tools wireless systems and networks.
ВСТУП 10 РОЗДІЛ 1 ВИБІР НАПРЯМКУ ТА ТЕМИ НАУКОВОГО ДОСЛІДЖЕННЯ 14 1.1 Завдання ідентифікації та аутентифікації користувача 14 1.2 Актуальні способи ідентифікації особи 23 1.3 Основні засади роботи систем біометричної ідентифікації 37 1.4 Описовий аналіз проблематики голосової ідентифікації 43 1.5 Висновки до розділу 1 46 РОЗДІЛ 2 МЕТОДОЛОГІЇ ОБРОБКИ ГОЛОСОВИХ СИГНАЛІВ ДЛЯ ЗАДАЧІ ІДЕНТИФІКАЦІЇ ОСОБИ 47 2.1 Завдання ідентифікації особи 47 2.2. Аналіз процедури утворення голосового сигналу та моделей процесу породження голосу 48 2.3 Основні вимоги до методології обробки аудіо сигналів для задачі голосової ідентифікації особи 56 2.4 Метод дослідження голосового сигналу з метою ідентифікації користувача 58 2.5 Висновки до розділу 2 62 РОЗДІЛ 3 ЕКСПЕРИМЕНТ З ВІДБОРУ ГОЛОСОВИХ СИГНАЛІВ 63 3.1 Обгрунтування структури експерименту з відбору голосових сигналів 63 3.2 Обгрунтування відбору параметрів мікрофона 64 3.3 Обгрунтування відбору параметрів АЦП у звуковій карті 65 3.4 Висновки розділу 3 67 РОЗДІЛ 4 ОБРОБКА ГОЛОСОВИХ СИГНАЛІВ З МЕТОЮ ІДЕНТИФІКАЦІЇ ОСОБИ 68 4.1 Визначення частотних параметрів формант голосових сигналів 68 4.2 Обчислення значень періоду основного тону голосових сигналів 70 4.3 Висновки до розділу 4 75 РОЗДІЛ 5 СПЕЦАЛЬНА ЧАСТИНА 77 5.1 Метрологічне забезпечення наукового дослідженя 77 5.2 Побудова прикладного програмного забезпечення для розв’язування наукової задачі 78 РОЗДІЛ 6 ОБҐРУНТУВАННЯ ЕКОНОМІЧНОЇ ЕФЕКТИВНОСТІ 85 6.1. Визначення стадій технологічного процесу та загальної тривалості проведення науково-дослідних робіт 85 6.2. Визначення витрат на оплату праці та відрахувань на соціальні заходи 88 6.3. Розрахунок витрат на електроенергію 92 6.4 Розрахунок витрат на матеріали 92 6.5 Розрахунок суми амортизаційних відрахувань 93 6.6 Обчислення накладних витрат 94 6.7 Складання кошторису витрат та визначення собівартості науково-дослідних робіт 95 6.8 Розрахунок ціни науково-дослідних робіт 96 6.9 Визначення економічної ефективності і терміну окупності капітальних вкладень 96 6.10 Висновок до розділу 6 98 РОЗДІЛ 7 ОХОРОНА ПРАЦІ ТА БЕЗПЕКА В НАДЗВИЧАЙНИХ СИТУАЦІЯХ 99 7.1 Охорона праці 99 7.2 Безпека в надзвичайних ситуаціях 110 РОЗДІЛ 8 ЕКОЛОГІЯ 114 8.1 Електромагнітне забруднення довкілля, його вплив на людину, шляхи його зменшення 114 8.2 Джерела шуму і вібрацій, методи їх знешкодження 116 ВИСНОВКИ 120 СПИСОК ВИКОРИСТАНИХ ДЖЕРЕЛ 122