Speaker’s Voice Recognition Methods in High-Level Interference Conditions

Юдін, О. К.; Зюбина, Руслана; Buchyk, Serhii; Bohuslavska, Olena; Teliushchenko, Valentyna

doi:10.1109/ukrcon.2019.8879937

Cited by 14 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, biometric authentication systems (BASs) [2] conduct user recognition based on their physiological and behavioral properties, which are known as biometrics [3], and hence are not trivially lost or forgotten. Voice, for example, is a biometric with great potential for applications in BASs [4], which defines voice-based authentication systems (VASs) [5]. Among the advantages of its use, we can highlight its uniqueness with the user, since each individual has a voice characterized by their unique vocal tract [6]; its ease of collection [7], since the biometrics reading is performed in a completely noninvasive way and without any physical interaction with devices, which also guarantees asepsis; a large quantity of literature [8] and computational packages [9] available for use; and the low cost of devices [10] used for collection, since any electronic system connected to a microphone can be used for this purpose [11].…”

Section: Introductionmentioning

confidence: 99%

An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection

Contreras

Viana

Fonseca

et al. 2023

Sensors

View full text Add to dashboard Cite

Biometrics-based authentication has become the most well-established form of user recognition in systems that demand a certain level of security. For example, the most commonplace social activities stand out, such as access to the work environment or to one’s own bank account. Among all biometrics, voice receives special attention due to factors such as ease of collection, the low cost of reading devices, and the high quantity of literature and software packages available for use. However, these biometrics may have the ability to represent the individual impaired by the phenomenon known as dysphonia, which consists of a change in the sound signal due to some disease that acts on the vocal apparatus. As a consequence, for example, a user with the flu may not be properly authenticated by the recognition system. Therefore, it is important that automatic voice dysphonia detection techniques be developed. In this work, we propose a new framework based on the representation of the voice signal by the multiple projection of cepstral coefficients to promote the detection of dysphonic alterations in the voice through machine learning techniques. Most of the best-known cepstral coefficient extraction techniques in the literature are mapped and analyzed separately and together with measures related to the fundamental frequency of the voice signal, and its representation capacity is evaluated on three classifiers. Finally, the experiments on a subset of the Saarbruecken Voice Database prove the effectiveness of the proposed material in detecting the presence of dysphonia in the voice.

show abstract

Section: Introductionmentioning

confidence: 99%

An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection

Contreras

Viana

Fonseca

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Biometrics [1] is defined as a physiological or behavioral attribute that can be used to uniquely characterize an individual. As examples, we can cite fingerprints [2], faces [3], iris [4], ears [5], voice [6], palmprint [7], body silhouette [8], walking way [9], among others. Based on these characteristics, user recognition systems can be defined, being this known as Biometric Authentication Systems (BASs) [10].…”

Section: Introductionmentioning

confidence: 99%

A New Multi-Filter Framework for Texture Image Representation Improvement Using Set of Pattern Descriptors to Fingerprint Liveness Detection

Contreras

Nonato

Boaventura³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

The use of user recognition and authentication systems has become very common and is part of everyday routines for many people, guaranteeing access to the automatic teller machines, entrance to the gym or even to smartphones. Among all the biometrics that can be analyzed in this type of system, the fingerprint is the most considered due to the ease of collection, the uniqueness of each user, and the large amount of solid theories and computational libraries available in the scientific literature. However, in recent years, the falsification of these biometrics with synthetic materials, known as spoofing, has become a real threat to these systems. To circumvent these effects without the addition of hardware devices, techniques based on the analysis of texture pattern descriptors were developed. In this work, we propose a new framework based on steps of data augmentation, image processing and replication, and feature fusion and reduction. The method has as main objective to improve the ability of classifiers, or sets of classifiers, to recognize life in fingerprints. Furthermore, it is proposed a generalization of vector representation of patterns described in matrix form from the systematic use of sets of mapping functions. All the proposed material was analyzed on the well-established benchmark of the Liveness Detection competition of the 2009, 2011, 2013 and 2015 editions, presenting an average accuracy of 97.77% and being a competitive strategy in relation to the other techniques that make up the state of the art of specialized literature.

show abstract

“…Such means of protection conduct dynamic and statistical analysis of files in a virtual environment and block various attacks if necessary [3,4].…”

Section: Introductionmentioning

confidence: 99%

Devising a method of protection against zero-day attacks based on an analytical model of changing the state of the network sandbox

Buchyk

Юдін

Зюбина

et al. 2021

EEJET

Self Cite

View full text Add to dashboard Cite

This paper reports a method of protection against zero-day attacks using SandBox technology based on the developed analytical model with a probabilistic ranking of information system states. The model takes into consideration the conditions of a priori uncertainty regarding the parameters of the destructive flow on the system, accounting for the typical procedures of the network SandBox. The proposed model of information system states makes it possible to analyze and track all possible states, as well as assess the level of security in these states, and the probability of transitions into them. Thus, it is possible to identify the most dangerous ones and track the activities that caused the corresponding changes. The fundamental difference between this model and standard approaches is the weight coefficients that characterize not the intensity of random events but the intensity of transitions between states. Direct implementation and application of the proposed analytical model involved the technology of multilevel network "SandBoxes". The difference from other popular anti-virus tools is the use of a priori mathematical threat assessment, which makes it possible to detect influences that are not considered threats by classical systems until the moment of harm to the system. The combination with standard security tools makes it possible to separately analyze files that are too large in size, whether they enter the system not through a common gateway controlled by the network "SandBox" but from the external media of end-users. The implementation of the developed analytical model has made it possible to improve the level of protection of the corporate network by 15 %, based on the number of detected threats. This difference is explained by the inability of classical software to detect new threats if they are not already listed in the database of the program, and their activity is not trivial

show abstract

Speaker’s Voice Recognition Methods in High-Level Interference Conditions

Cited by 14 publications

References 9 publications

An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection

An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection

A New Multi-Filter Framework for Texture Image Representation Improvement Using Set of Pattern Descriptors to Fingerprint Liveness Detection

Devising a method of protection against zero-day attacks based on an analytical model of changing the state of the network sandbox

Contact Info

Product

Resources

About