Speech Information Research Articles

Effect of hearing experience on preschool-aged children's eye gaze to a talker during spoken language processing.

Speechreading-gathering speech information from talkers' faces-supports speech perception when speech acoustics are degraded. Benefitting from speechreading, however, requires listeners to visually fixate talkers during face-to-face interactions. The purpose of this study is to test the hypothesis that preschool-aged children allocate their eye gaze to a talker when speech acoustics are degraded. We implemented a looking-while-listening paradigm to quantify children's eye gaze to an unfamiliar female talker and two images of familiar objects presented on a screen while the children listened to speech. We tested 31 children (12 girls), ages 26-48months, who had normal hearing (NH group, n = 19) or bilateral sensorineural hearing loss and used hearing devices (D/HH group, n = 12). Children's eye gaze was video-recorded as the talker verbally labeled one of the images, either in quiet or in the presence of an unfamiliar two-talker male speech masker. Children's eye gaze to the target image, distractor image, and female talker was coded every 33ms off-line by trained observers. Bootstrapped differences of time series (BDOTS) analyses and ternary plots were used to determine differences in visual fixations of the talker between listening conditions in the NH and D/HH groups. Results suggest that the NH group visually fixated the talker more in the masker condition than in quiet. We did not observe statistically discernable differences in visual fixations of the talker between the listening conditions for the D/HH group. Gaze patterns of the NH group in the masker condition looked like gaze patterns of the D/HH group.

Speechreading ability is related to phonological awareness and reading comprehension in adults with hearing impairment in China

ABSTRACT We investigated whether phonological awareness mediated the relationship between speechreading and reading comprehension in Chinese adults with hearing impairment (HI) and normal hearing (NH). Speechreading, phonological awareness, and reading comprehension tests were administered to 154 young adults with HI and 97 young adults with NH in China. Results revealed significant correlations between speechreading, phonological awareness, and reading comprehension in adults with HI, but not those with NH. Phonological awareness did not mediate the relationship between speechreading and reading comprehension in either group of participants. These results suggest that visual speech information (speechreading) contributes to the development of phonological representations in adults with HI, which in turn supports reading comprehension. This relationship was not observed in the adults with NH. Teachers and clinicians working with HI students need to have an understanding of this difference, and take into account the developmental nature of the relationship between speechreadaing, phonological awareness and reading comprehension in the HI students for differentiated reading intervention. If attention to the visual speech information via speechreading indeed contributes to better phonological awareness, HI students may benefit from other visual methods to develop component skills that are foundational to reading success.

Bahasa Persuasi dalam Video YouTube Food Vlogger MGDALENAF

A food vlogger's language of persuasion plays an important role in influencing viewership. It can arouse curiosity, whet appetites, and create emotional attachments with video viewers. In the midst of increasing content competition, the urgency of this study is to revisit the accuracy of word choice and easy-to-understand delivery to attract viewers. This article aims to identify persuasive forms in the YouTube videos of food vlogger MGDALENAF. The method used in this research is a qualitative method. The video transcription process uses the listening method, then the persuasive forms of MGDALENAF's speech are analyzed using the commensurate method and presented informally. The results of this study show a variety of assertive, directive, and expressive speech acts for certain purposes. Assertive speech acts are used for convincing actions. Directive speech acts are used for suggestion and invitation. Expressive speech acts are used for the act of praising. The dominance of speech used by MGDALENAF food vloggers is in the form of statement sentences and command sentences. The persuasion language used by MGDALENAF food vloggers is personal, casual, and not pushy. This casual nature then has an impact on the number of video viewers and the increasing interest of viewers to visit the culinary recommendations suggested by MGDALENAF food vloggers.

Ethnolinguistic peculiarities of the language of ‘power’ on the material of historical and legendary heroes of Yakuts

The article focuses on the study of the language of "power" based on the speech forms of Tyghyn Darkhan, a historical figure of the Sakha people, conducted within the framework of ethnolinguistic analysis. The relevance of the research is determined by the need for an in-depth examination of the phenomenon of leadership in the national settlements of the Russian Arctic, as well as the analysis of grassroots perceptions of state governance. This study, based on Yakut folklore materials, contributes to expanding knowledge about the mechanisms of power and leadership in northern sociocultural contexts. The novelty of the study lies in its first-ever approach to analyzing the language of "power" through the lens of Yakut folklore, which allows for the identification of unique features of political discourse. This opens up opportunities to analyze rhetorical strategies, manipulative techniques, and mechanisms for achieving balance in relationships between power and society. The research aims to analyze the language of "power" through the speech forms of Tyghyn Darkhan to identify the ways leadership qualities were constructed and power relationships were established in traditional Sakha society. To achieve this goal, folklore sources related to the image of the hero were studied, key linguistic tools were identified, and their functional roles in political discourse were analyzed. The methodological foundation of the study includes descriptive, comparative-historical, semantic, and discourse analysis. Particular attention is paid to the interpretation of texts in their cultural and historical context. The results demonstrate that Tyghyn Darkhan's language played a significant role in consolidating his authority, fostering social integration, and regulating societal relations. His rhetorical strategies combined traditional and innovative approaches, highlighting his importance for understanding the mechanisms of power in ethnic communities. The findings make a substantial contribution to the development of ethnolinguistics and political anthropology. Future research prospects include extending the analysis to the linguistic practices of other northern peoples, which will deepen the understanding of the role of language in sociopolitical processes in Arctic regions.

(Re)constructing ambivalent identities in Zahia Rahmani’s France: récit d’une enfance (2006) and Alice Zeniter’s L’Art de perdre (2017)

This article examines multivocal, intersubjective explorations of ambivalent identity in two literary works centring female descendants of harkis (Algerian auxiliary soldiers enlisted in the French army during the Algerian War). Zahia Rahmani’s France: récit d’une enfance (2006) and Alice Zeniter’s L’Art de perdre (2017) document their protagonists’ struggles to reconstruct, and simultaneously reconfigure or subvert, complex memories and identities fragmented by colonial history and its afterlives. Plural, often transgressive, forms of speech, dialogue, and storytelling are shown to facilitate explorations of ambivalent intergenerational and intercultural affect, also emerging as forces of critique, resistance, and interpellation. In their navigation of conflictual, ambiguous histories that place diverse memories and identities in productive tension, both texts complicate notions of belonging and inheritance. Their layered, dialogic narrative quests treat subjectivity, memory, and temporality as plural, fluid, and contingent, resisting straightforward identification with a singular identity marker, whether harki , Algerian, Amazigh (Berber), French, or otherwise. Crucially, through the real and imagined landscapes they traverse, they also turn outwards in their questioning of broader oppressive, traumatogenic structures and reductive narratives. ‘Pre-written’ narratives, whether involving colonial or contemporary Algeria, the experiences of the harkis or those of rural French communities, are thus deconstructed and rewritten. Drawing on theorizations and interrogations of postcolonial hybridity and witnessing, this article argues that these narrative (re)constructions privilege neither unified subjectivity nor potentially essentialized forms of fragmentary identity. Citing yet interrogating institutionalized narratives of memorialization, reconciliation, and reparation, Rahmani and Zeniter present ambivalent, fractured intergenerational transmission as a shifting locus of encounter, exchange, and contestation.

The Greek left-wing and the ‘Jewish problem’: analysing antizionism and antisemitism as forms of soft hate speech

ABSTRACT This paper seeks to explore whether and how the Greek left-wing criticism against Israeli politics challenges the state of Israel’s right to exist and spreads antisemitic mythopoesis by utilising ‘soft hate speech’. In particular, my aim is to shed light on an ideological paradox – the utilisation of discriminatory discourse by the Greek left – a multidimensional political power consisted of a wide range of ideologies that all defend human rights and are characterised by progressive perspectives; a point that reveals that antisemitism is well rooted in the Greek society, revives in times of crisis and penetrates the whole political spectrum. By applying the Discourse Historical Approach (DHA) to Critical Discourse Studies (CDS) and its argumentation strategies as an appropriate theory and methodology to analyse in detail such utterances, my attempt is to show how antisemitism has been constituted as a common sense beyond the limits of the far-right populist discourses.

Aspects of the dialogue in virtual communication (the dialogue in the comments section)

Dialogue as a form of communication is part of virtual communication on the Internet. Comments are a type of dialogue that is characterized by distance between communicators, indirectness and one-way communication. Linguistically, commentary is a written form of spoken speech, in which almost all communicative practices inherent in oral speech are observed. In this study, comments on the Facebook pages of four entertainment television shows are analyzed. The speech strategies and linguistic devices used in the comments as a dialogic form are analyzed.

Analisis Cyberbullying pada Game Online Valorant: Studi pada Communication Abuse Antarpemain

Competitive online games such as Valorant as a new medium that provides an interactive and competitive virtual space for online game players. Tension and excitement between players in competing often triggers the emergence of Cyberbullying behavior. Cyberbullying itself is the behavior of game players in the form of hate speech or negative actions that affect communication between online game players. However, researchers see that each player is different in responding to Cyberbullying carried out by other players and their teams. This study aims to find out how the factors, forms and responses of victims in doing, responding to communication abuse. The method in this study uses qualitative descriptive research. The results of the study show that Cyberbullying in the online game Valorant shows that the communication abuse factor is caused by other players who play badly, while the forms are carried out in the form of verbal through text or voice, as well as the response of the victims tends not to care and stay focused on the game to try to save it despite the bad treatment from other players.

Analysis of Function of Tact Maxim in the Event of Marhata Sinamot Speech of Batak Toba Traditional Weddings

This research aimed to describe the tact maxim in the event of Marhata sinamot of Batak Toba tradition that reviewed its function namely assertive, directive, commissive, expressive and declarative. This research used a qualitative descriptive approach; the data collection technique involved interviewing and recording, while the analysis data was described, and conclusions were made. The result showed that the tact maxim is one of the principles of politeness whose form of speech prioritizes the benefits of others and reduces/maximizes one's own benefits. From the results obtained, there are (2) assertive utterances, (10) directive utterances, (1) commissive utterances, (3) expressive utterances, and (1) declarative utterances. The dominant tact maxim based on its function was found in the directive speech act.

ANALISIS TINDAK TUTUR DIREKTIF ANAK USIA PRASEKOLAH DI LINGKUNGAN BERMAIN

The importance of analyzing directive speech acts in preschool-aged children needs to be carried out to see how preschool-aged children act. At pre-school age, children experience rapid language development. Understanding the speech acts of pre-school children helps parents and educators support the language learning process effectively. The research was conducted at Timezone Lampung City Mall, this research data is directive speech acts of preschool children aged 5-6 years. The research subjects were children aged 5-6 years who played at Timezone Lampung City Mall. Based on the results, it can be seen that the forms of directive speech acts found in preschool children (5-6 years) at Timezone Lampung City Mall are in the form of requests, questions, commands, prohibitions and advice. There were no directive speech acts found in children's speech. The results of the research show that children's early speech repertoires are limited, transitional, and imperfectly language-like to a certain extent. Most of the linguistic forms acquired by children are expressions that lack the characteristics of syntactic combinations in adult language. The most dominant types of directive speech acts that often appear in the speech of preschool aged children are the types of directive speech acts of questions and commands. These two types of directive speech acts are the most prominent and are widely used by children to ask, order, and ask to remind.

Analisis Kasus Peretasan Media Sosial melalui Digital Forensik sebagai Upaya Preventif Penyidik Mencegah Kejadian Salah Tangkap

Digital Forensics in Uncovering Social Media Hacking Events as a Tool to Help the Police to Fulfil Evidence. Normative legal research or library research, with a statute approach, conceptual approach, comparative approach, historical approach. The nature of the research used in this research is descriptive-prescriptive, the author uses content analysis. The role of digital forensics in finding scientific and objective results as a solid foundation that the police must have from the beginning of the legal process according to researchers is quite important. Because digital forensics is the basis, guidelines and reference for the forensic laboratory centre in acting to examine evidence in the form of speech or invitations made by Ravio Patra's social media account whether it is true that he himself did it or whether there is a hacking factor.

Religious Hate Speech against Islam in Bollywood Cinema in the Context of Self-Orientalism: The Example of “The Kerala Story”

Hate speech, which refers to any form of expression intended to humiliate, harass, intimidate or incite violence against a person or group because of their religion, language, race, gender, political preference, physical disability or illness, occurs in different societies and in different media. Undoubtedly, one of the most common forms of hate speech is religious hate speech. Religious hate speech, which causes great harm to the individual, group or society, when carried out through cinema, causes victimization to increase and the discourse to spread throughout the world. Religious hate speech, generally produced by the West towards the East in cinema, sometimes comes to life with self-orientalist actions and religious hate speech is reinforced. From this point of view, the aim of this study is to reveal how religious hate speech against Islam and Muslims is realized in the context of self-orientalism in Bollywood cinema. In the study, critical discourse analysis method was used and the 2023 Indian film ‘The Kerala Story’ was analyzed. According to the results obtained in the study, the film, which was designed with a self-orientalist perspective, contains intense religious hate speech against Islam. In the film, Islam and Muslims are associated with terrorism through characters, actions, lines and plot.

მონოლოგური და დიალოგური დისკურსი და მიმართვის ფორმები პიერ კორნელის „ჰორაციუსის“, „ცინას“ და „პომპეუსის სიკვდილის“ მიხედვით

In Pierre Corneille's "Roman Tragedies"-“Horace”, “Cinna” and “The Death of Pompey” the types of dramatic discourse – dialo­gues and mono­logues – occupy an important place. Dialogues and monologues have the function of self-expression of the characters. Monologue is one of the best ways to illustrate the characters' thoughts and inner feelings. According to the poetics of classicism, when the character is alone on stage, the principle of persuasiveness requires that he express his thoughts, which he often expresses in the form of a dialogue with himself, which he or she does not want anyone to hear. Through the monologue of the characters of Corneille's tragedies they not only carefully examine the hidden sides of their souls and convince themselves of the necessity of certain actions, but also examine and review possible decisions and the advantages and disadvantages of these decisions. In “Horace”, “Cinna” and “The Death of Pompey” the mono­lo­gue has the following functions: Through monologue, the actors of the tragedy express their personal feelings and attitudes. Through monologue, the characters of the tragedy judge and analyze this or that idea and point of view. Dialogue, like monologue, is a basic and important form of dramatic speech. P. Cornielle perfectly uses dialogues in "Roman tra­gedies" for the purpose of exchange of ideas between actors, tho­rough reasoning about the problem and persuasion of the interlocutor. Corneille's emotionally charged dialogues with a high tragic register express the pathos and ethos of the actors, their thoughts and inner feelings. In “Horace”, “Cinna” and “The Death of Pompey” Pierre Cor­neille, in addition to monologue and dialogic discourse, uses such rhetorical-stylistic means as: formal ("you") and informal ("you") forms of address and apos­trophes – "Seigneur", "Madame", "Princess", "Prince", "reine" and others. The use of the formal – "you" form of address is related to the rule accepted in the aristocratic society of France during the Pierre Corneille era, according to which the aristocracy mainly used the formal "you" of address in the 17th cen­tury. Pierre Corneille created tragedies, first of all, for the king and the society of the royal court, and the vocabulary of the acting heroes of the tragedy should be high and pathetic. As for the „you“ informal of address, its use by the characters indicates their emotional change, and the use of apostrophes orga­nizes the inter­locutive space in which the speakers, using evidence, in a state of emotional rapture or affect, directly convey what they have to say.

ОСОБЛИВОСТІ ВИКЛАДАННЯ АНГЛІЙСЬКОЇ МОВИ ЗА ДОПОМОГОЮ ПОДКАСТІВ У НЕФОРМАЛЬНІЙ ОСВІТІ

The aim of the article is to analyse the peculiarities of teaching English with podcasts. This aim involves solving the following research tasks: to find out the stages of creating podcasts for teaching and learning English for self-education. Methodology: the aim and tasks of the research have been achieved by using such research methods as analysis of scientific pedagogical and methodological sources in teaching English using podcasts; development of a project on teaching English using podcasts for self-education of the adult generation. Scientific novelty. The article analyses the positive and negative aspects of teaching English as a foreign language using podcasts in formal, non-formal and informal education. The results of the study show that teaching English using podcasts can be implemented in formal, non-formal and informal education. Based on the research, it has been found that non-formal education in teaching English is an institutional, targeted and planned education by individuals or organisations that provide didactic, socio-pedagogical, vocationally oriented, linguistic, cultural, anagogical and distance educational services for learning English at a certain level. It is noted that in order to improve the level of English-language communicative competence for professional and everyday communication in various communication situations, it is desirable to create courses for their employees at enterprises. It is emphasised that for better mastering of the English language learning material, it is necessary to create and use podcasts. Based on the study by S. Y. Nikolaieva, their main features (efficiency, effectiveness, ergonomics and high motivation) are taken into account to increase interest in non-formal education and improve personal abilities and facilitate further learning of students in non-classroom environment. The analysis of the study on the use of podcasts in education shows that podcasts are an important and relatively new teaching tool that teachers can use to avoid standard teaching methods. Practical significance. The study reveals the peculiarities of creating and using podcasts in non-formal education, namely in teaching English language learners in non-classroom environment. Such platforms as Twitter, Instagram and YouTube are creating new opportunities for learning English. Podcasts have their own peculiarities: accessibility, presentability and independence. The article analyses the advantages and disadvantages of audio podcasts. Conclusions and further research perspectives. Creating a podcast is a complicated process that requires planning and implementation of several stages (planning a podcast, selecting educational material, editing and publishing educational material, creating a trailer and designing a podcast cover, producing podcasts). It is noted that podcasts are a kind of digital archive that stores language and speech information for a long time and makes them available to the audience. Value (originality). The value of the study is characterized by the presentation of a new vision of the peculiarities of creating and using podcasts in non-formal education, namely in teaching English language learners in non-classroom environment. Key words: podcasts, non-formal education, self-education, teaching English.

振兴语言能力：双峰静默交互系统

Vocal disorders due to laryngeal cancer, cerebral palsy, autism, autism and other complicated diseases makes rehabilitation very difficult. Most patients are unable to communicate reliably or easily using their natural voice. Studies have shown that most patients have laryngeal motor capabilities. The laryngeal vibrations as well as muscle activity related to vocal system contain rich speech information. Hence, by monitoring and deciphering laryngeal movement data, we can facilitate silent communication, offering potential relief to individuals coping with vocal disorders, enabling them to “articulate their thoughts and reclaim their voices”.The signals of silent interaction systems stem from laryngeal electromyographic signals or vibration signals, resulting in a single dimension of sensed signals, limiting voice recognition, and challenges in sensor adherence to the skin. Therefore, there is a need to develop a wearable, non-invasive silent interaction system to facilitate seamless communication for individuals grappling with vocal impairments. In this paper, we introduce a bimodal voiceless interaction system which aims to achieve the monolithic integration of myoelectric and pressure sensors using micro-nano processing techniques. Through the correlation of laryngeal myoelectric signal and the vibration mechanics signal with speech signal, and the integration of signal acquisition, transmission, machine learning algorithms and speech recognition, our aim is to achieve highly precise sound signal output. This initiative endeavors to surpass the constraints of current voiceless interaction interfaces, addressing issues such as signal perception limitations, low sound recognition rates, and single-dimensional voice recognition constraints. The specific work of this paper includes:(1) Explore the sensing mechanism of bimodal sound signalsWe construct a quantized flexible piezoelectric pressure sensor model and an electrode-skin electrical model to investigate impedance measurement mechanisms and their performance with diverse electrode materials. Furthermore, we create a macroscopic model of the gel muscle electrode in the larynx to clarify the interplay among various sensing parameters, including sensitivity, motion artifacts, frequency response, and impedance.(2) Prepare high-performance hydrogel materialsWe explore the preparation process of PVA hydrogel material, concentrating on designing doping formulations, enhancing biocompatibility modification, improving adhesion and conductivity, and implementing other performance improvements. This includes modifying hydrogels using both natural polymer materials and synthetic polymers. We introduce a preparation method of throat PVA hydrogel muscle electrode and produce gel electrode with enhanced adhesion and conductivity.(3) Design and fabricate bimodal sensorsWe utilize a PVDF piezoelectric film as the sensing unit to capture laryngeal kinematic mechanical signals, while exploring processing and encapsulation techniques for PVDF pressure sensors. For laryngeal electromyographic signals, we utilize PVA hydrogel as the sensing unit, investigating the preparation and encapsulation process for multi-channel laryngeal muscle electrode arrays. Finally, we devise a range of integration and encapsulation methods for bisensory devices, introducing wearable bimodal sensors distinguished by their comfort, convenience and reliability.(4) Construct bimodal silent interaction system and verify speech recognition functionUtilizing the bimodal signals generated by the pressure sensor and the laryngeal EMG sensor, we engineer a high-quality sensing signal transfer and readout circuit. We investigate noise reduction and filtering algorithms for the bimodal signals, and design models for signal enhancement, feature extraction, fusion, and recognition. Subsequently, we construct the bimodal silent interaction system and verify its functionality and reliability. Figure 1

«Spanish Noir»: towards a Literary Understanding of Genre (on the Example of the Novel «Todo esto te daré» by D. Redondo)

The theoretical orientation of the article pursues a practical purpose: to embed a sample of contemporary Spanish crime literature in the genre framework and to be able to apply the results obtained in this type of works. The issue of genre attribution in crime literature has not yet been resolved due to the different starting points of numerous approaches: genre genesis, national specifics, gender perspective, stylistics, etc. Our hypothesis consists in the possibility of attributing any sample of modern criminal literature to a certain genre on the basis of unified literary parameters regardless of the national origin of the work. The artistic analysis of Dolores Redondo’s novel «Todo esto te daré» (2016) on the basis of the genre-typological method – is preceded by theoretical sections. In the introduction, the expediency of this study in the light of the influence of publishing practices on the literary component itself is substantiated. The issue of genre determination is often distorted for the sake of commercial success, depriving researchers of the possibility of scientific analysis using unified terms. Turning directly to the subject of the study, we offer a short excursion into the history of Spanish crime literature and into the environment of scholarly reflection on the so-called «noir» – frequent, but lacking terminological nomination. The methodology proposed by N.N. Kirilenko and O.V. Fedunina becomes the main tool for analyzing the text. The consistent «filtering» of the novel through the constant structural features (type of hero, subject structure, chronotope, and compositional forms of speech) allows it to be attributed to the genre of “victim investigation” with some features of a police novel. The search for the genre of a work in a synchronic context is convenient and universal, therefore, firstly, it is applicable to almost all samples of modern criminal literature, and secondly, it can be complementarily combined with other research purposes. So, you can focus on the genesis of the genre or various factors influencing it in the past and present. In any case, for all the mobility and hybrid nature of contemporary crime literature, its samples can be classified according to uniform criteria, which significantly enriches the toolkit for further research.

Predicting the intelligibility of Mandarin Chinese with manipulated and intact tonal information for normal-hearing listeners.

Objective indices for predicting speech intelligibility offer a quick and convenient alternative to behavioral measures of speech intelligibility. However, most such indices are designed for a specific language, such as English, and they do not take adequate account of tonal information in speech when applied to languages like Mandarin Chinese (hereafter called Mandarin) for which the patterns of fundamental frequency (F0) variation play an important role in distinguishing speech sounds with similar phonetic content. To address this, two experiments with normal-hearing listeners were conducted examining: (1) The impact of manipulations of tonal information on the intelligibility of Mandarin sentences presented in speech-shaped noise (SSN) at several signal-to-noise ratios (SNRs); (2) The intelligibility of Mandarin sentences with intact tonal information presented in SSN, pink noise, and babble at several SNRs. The outcomes were not correctly predicted by the Hearing Aid Speech Perception Index (HASPI-V1). A new intelligibility metric was developed that used one acoustic feature from HASPI-V1 plus Hilbert time envelope and temporal fine structure information from multiple frequency bands. For the new metric, the Pearson correlation between obtained and predicted intelligibility was 0.923 and the root mean square error was 0.119. The new metric provides a potential tool for evaluating Mandarin intelligibility.

Towards a Federal-Type Regulation of Online Public Discourse by the EU?

This article analyses the federal dimension of the European Union’s (EU) regulation of online public discourse, which is a dimension of the European integration process not extensively explored. In this article, ‘online public discourse’ refers to the regulation of those forms of speech that are functional to the democratic debate, from the dissemination of news to political communication, and that take place on digital platforms. The Digital Services Act (DSA) and other recent regulations have changed the type of regulation applied by the EU. Does this regulation have a federal nature? To address this research question, the EU regulation of online public discourse is compared with the regulation in the United States. Through a comparative law methodology and a comparison with what has occurred in the United States in the regulation of online public discourse, the article argues that this EU regulation of public discourse exhibits the characteristics of a federal regulatory arrangement.

Feature-level fusion of face and speech based multimodal biometric attendance system with liveness detection

The rapid growth of deep learning and the Internet of Things has spurred the need for touchless biometric systems in areas where cleanliness and non-intrusive user interaction are critical. In order to authenticate seamlessly, traditional biometric methods such as fingerprint, hand, etc. recognition require physical contact and, therefore, risk hygiene issues, hence making face and speaker verification more viable alternatives. A robust Multimodal Biometric Attendance System (MBAS) is needed due to the vulnerabilities and limitations of single modality systems. In this research, we introduce MBAS using feature-level fusion of speech data with face data, combining the best of both worlds. The textural features based on a person’s facial appearance are integrated with dynamic speech information for liveness detection, followed by dimensionality reduction using linear discriminant analysis, and then incorporated into a Bi-LSTM classifier. Therefore, for better security, accuracy, and anti-spoofing attacks, this approach is proposed in addition to increasing accuracy as well as enhancing security against spoofing attacks. Two publicly available datasets, DeepfakeTIMIT and AVSpeech, are extensively explored to evaluate different fusion strategies, classifier types, and standard performance metrics. The proposed system outperformed other cutting-edge biometric based systems by exhibiting a 97.51% high accuracy rate with a precision of 99.10% and an equal error rate of 2.48%. These findings affirm the effectiveness and possible real-world applications of the MBAS concept, along with its enhancement ensuring safety. Furthermore, this study underscores the importance of incorporating advanced liveness detection into secure contactless biometrics solutions for modern attendance management in various industries that encompass both face and voice modalities.

Predictive brain activity related to auditory information is associated with performance in speech comprehension tasks in noisy environments.

Understanding speech in noisy environments is challenging even for individuals with normal hearing, and it poses a significant challenge for those with hearing impairments or listening difficulties. There are limitations associated with the current methods of evaluating speech comprehension in such environments, especially in individuals with peripheral hearing impairments. According to the predictive coding model, speech comprehension is an active inference process that integrates sensory information through the interaction of bottom-up and top-down processing. Therefore, in this study, we aimed to examine the role of prediction in speech comprehension using an electrophysiological marker of anticipation: stimulus-preceding negativity (SPN). We measured SPN amplitude in young adults with normal hearing during a time-estimation task with auditory feedback under both quiet and noisy conditions. The results showed that SPN amplitude significantly increased in noisy environments. Moreover, individual differences in SPN amplitude correlated with performance in a speech-in-noise test. The increase in SPN amplitude was interpreted as reflecting the increased requirement for attentional resources for accurate prediction of speech information. These findings suggest that SPN could serve as a noninvasive neural marker for assessing individual differences in top-down processing involved in speech comprehension in noisy environments.