Search Results (12)

Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disorder that progressively impairs motor and communication abilities. Globally, the prevalence of ALS was estimated at approximately 222,800 cases in 2015 and is projected to increase by nearly 70% to 376,700 cases by 2040, primarily driven by demographic shifts in aging populations, and the lifetime risk of developing ALS is 1 in 350–420. Despite international advancements in assistive technologies, a recent national survey in Saudi Arabia revealed that 100% of ALS care providers lack access to eye-tracking communication tools, and 92% reported communication aids as inconsistently available. While assistive technologies such as speech-generating devices and gaze-based control systems have made strides in recent decades, they primarily support English speakers, leaving Arabic-speaking ALS patients underserved. This paper presents SOUTY, a cost-effective, mobile-based application that empowers ALS patients to communicate using gaze-controlled interfaces combined with a text-to-speech (TTS) feature in Arabic language, which is one of the five most widely spoken languages in the world. SOUTY (i.e., “my voice”) utilizes a personalized, pre-recorded voice bank of the ALS patient and integrated eye-tracking technology to support the formation and vocalization of custom phrases in Arabic. This study describes the full development life cycle of SOUTY from conceptualization and requirements gathering to system architecture, implementation, evaluation, and refinement. Validation included expert interviews with Human–Computer Interaction (HCI) expertise and speech pathology specialty, as well as a public survey assessing awareness and technological readiness. The results support SOUTY as a culturally and linguistically relevant innovation that enhances autonomy and quality of life for Arabic-speaking ALS patients. This approach may serve as a replicable model for developing inclusive Augmentative and Alternative Communication (AAC) tools in other underrepresented languages. The system achieved 100% task completion during internal walkthroughs, with mean phrase selection times under 5 s and audio playback latency below 0.3 s. Full article

Is negation negative? For some authors, in some languages, it is not. This is the case for so-called strict negative concord languages (e.g., Russian), in which negation is taken to be non-negative, following the cross-linguistic analysis for negative concord systems proposed by Hedde Zeijlstra’s work “Sentential negation and negative concord”. However, this analysis is focused on languages with SVO word order. In this paper, I propose to reconsider the typology of negative concord by zooming out of the focus on SVO languages that current literature has relied on. I discuss the case of SOV languages where observing a strict NC pattern leads to weaker conclusions about the nature of negation than for SVO languages with strict negative concord, leaving the negativity status of negation in those languages underdetermined. I then take a look at Turkish, an SOV language with three sentential negation markers: plain sentential negation -mA, copular negation değil, and existential negation yok. Evidence from the interaction of these markers with neither..nor phrases suggests that değil and yok, in contrast with -mA, are non-negative for some speakers. In order to explain the variation, I put forward a hypothesis about the learning process, in which there is sometimes insufficient evidence in the input to determine whether değil and yok are negative, and learners choose between two conflicting heuristics that result in the negativity or non-negativity of these markers. Full article

Feature extraction for speech emotion recognition (SER) has evolved from handcrafted techniques through deep learning methods to embeddings derived from pre-trained models (PTMs). This study presents the first comparative analysis focused on using PTMs for Spanish SER, evaluating six models—Whisper, Wav2Vec 2.0, WavLM, HuBERT, TRILLsson, and CLAP—across six emotional speech databases: EmoMatchSpanishDB, MESD, MEACorpus, EmoWisconsin, INTER1SP, and EmoFilm. We propose a robust framework combining layer-wise feature extraction with Leave-One-Speaker-Out validation to ensure interpretable model comparisons. Our method significantly outperforms existing state-of-the-art benchmarks, notably achieving scores on metrics such as F1 on EmoMatchSpanishDB (88.32%), INTER1SP (99.83%), and MEACorpus (92.53%). Layer-wise analyses reveal optimal emotional representation extraction at early layers in 24-layer models and middle layers in larger architectures. Additionally, TRILLsson exhibits remarkable generalization in speaker-independent evaluations, highlighting the necessity of strategic model selection, fine-tuning, and language-specific adaptations to maximize SER performance for Spanish. Full article

Background: Cognitive impairment poses a significant global health challenge, emphasizing the critical need for early detection and intervention. Traditional diagnostics like neuroimaging and clinical evaluations are often subjective, costly, and inaccessible, especially in resource-poor settings. Previous research has focused on speech analysis primarily conducted using English data, leaving multilingual settings unexplored. Methods: In this study, we present our results from the INTERSPEECH 2024 TAUKADIAL Challenge, where we aimed to automatically detect mild cognitive impairment (MCI) and predict cognitive scores for English and Chinese speakers (169 in total). Our approach leverages Whisper, a speech foundation model, to extract language-agnostic speech embeddings. We then utilize ensemble models to incorporate task-specific information. Results: Our model achieved unweighted average recall of 81.83% in an MCI classification task, and root mean squared error of 1.196 in cognitive score prediction task, which placed the model at the second and the first position, respectively, in the ranking for each task. Comparison between language-agnostic and language-specific models reveals the importance of capturing language-specific nuances for accurate cognitive impairment prediction. Conclusions: This study demonstrates the effectiveness of language-specific ensemble modeling with Whisper embeddings in enabling scalable, non-invasive cognitive health assessments of Alzheimer’s disease, achieving state-of-the-art results in multilingual settings. Full article

Syntactic priming in dialogue occurs when exposure to a particular syntactic structure implicitly induces a speaker’s subsequent preference for the same syntactic structures in their own speech. Here, we asked whether this priming effect is boosted when individuals are primed by several different speakers as opposed to one. In an initial baseline session involving a picture description task, we assessed adult participants’ production of double object/DO (vs. prepositional/PO) dative and passive (vs. active) transitive structures. Subsequently, participants played a picture description and verification game, in turns, with six other players (confederates). During verification turns, confederates primed participants by using DO and passive utterances. Crucially, participants were primed either by a single confederate (single-speaker priming condition, SSP) or by five confederates (multi-speaker priming condition, MSP). Across conditions, the same priming stimuli were presented in the same order, leaving speaker source/variation as the only different feature. The degree to which participants were primed for the target structures compared to baseline was measured. Results indicated a robust priming effect in both conditions. Nevertheless, the increase in the target structures’ use did not differ significantly between the SSP and MSP conditions, suggesting that speaker variation did not promote stronger priming. Full article

The current paper explores language contact between two Greek varieties, Pontic Greek and Cypriot Greek, in the northern part of Cyprus. After the de facto partition of Cyprus in 1974, several Pontic Greek-speaking communities were transplanted from their homeland in Trabzon to the peninsula of Karpasia in northern Cyprus. These “newcomers” or “immigrants” or “settlers” were brought from Turkey after the displacement of the Greek Cypriot population living in the north. Hence, from 1976 another Greek linguistic variety emerged in the area, Pontic Greek or Romeyka or Rumca, which was the home variety of the newcomers. Although Greek Cypriots were forced to leave the area, Cypriot Greek retained a strong presence in Karpasia, spoken by Turkish Cypriot Romeika speakers and by Greek Cypriots who remained “enclaved” in some villages of the peninsula. Hence, a dynamic and multifacet sociolinguistic context has been created where two main non-standard varieties of the Greek language, Cypriot Greek and Pontic Greek, are in contact and are spoken by different groups of speakers and where Turkish remains the dominant and official language. Within this context, the current paper explores instances of language contact between Pontic Greek and Cypriot Greek, focusing on the narratives produced by Pontic Greek speakers. The paper employs ethnographic methods for approaching these communities and for understanding issues of language use and language values within a heavily politicized context. The theoretical constructs of space and border are used to interpret the data and provide a deeper understanding of language contact, daily practices, and wider ideologies. Full article

This paper investigates additive links to discourse alternatives in picture comparison dialogues produced by adult native speakers of English and German. Additive relations are established across turns when participants are confirming the presence of matching objects on both pictures (A: “I have X”. B: “I also have X”). Speakers thereby describe their own picture and construe the interlocutor (or rather: the interlocutor’s picture) as a discourse alternative. Whereas the vast majority of the confirming descriptions in German contain an additive particle (auch), less than half of the corresponding confirmations in the English data do (“also”, “too”, etc.). Numbers differ even more drastically in polarity questions (“Do you (also) have X?”) that are equally typical for the dialogue task. Such frequency differences are at odds with recent accounts treating additive particles as being quasi obligatory when their presupposition is satisfied. An in-depth contrastive analysis of lexical, syntactic and information structural properties reveals that the default mapping of information units on syntactic functions (subject) in conjunction with the SVO word order of English leads to a structure in which subject, initial (topic) position and the particle’s associated constituent coincide. This would make the relation to its discourse alternative more prominent than warranted by the dialogue task and speakers of English leave this relation unmarked or resort to alternative constructions instead. The V2 syntax of German, on the other hand, allows for a dissociation of discourse topic and associated constituent. It allows the speaker to topicalize reference to the matching object, to highlight the confirmation of its presence on the speaker’s picture, and to relate the changing information to its discourse alternative in a non-contrastive way. Full article

The Old English poem in The Exeter Book titled The Wife’s Lament is about longing and loneliness; the woman speaking in the poem longs for her absent husband who has sent her to live in a “cave under an oak tree”. The husband’s attitude toward his wife is a major point of controversy among commentators on the poem: has he sent her there as a punishment or for her protection? This essay argues that he loves her and seeks to protect her in his absence. The argument supporting this view addresses the following three topics: the reason he must leave and his brooding silence preceding that departure, the culture of warrior oaths, and the nature of the “cave” where the speaker is located. The first two discussions assess and reframe previous scholarship, while the discussion of the speaker’s location introduces a new area of research, the archaeology of early medieval rock-cut buildings. Finding that the poet might imagine the Wife inhabiting such a constructed building invites us to think about her, her husband, the poem, and even the Exeter Book itself within a new and interesting real-world context. Full article

Communication has been an important aspect of human life, civilization, and globalization for thousands of years. Biometric analysis, education, security, healthcare, and smart cities are only a few examples of speech recognition applications. Most studies have mainly concentrated on English, Spanish, Japanese, or Chinese, disregarding other low-resource languages, such as Uzbek, leaving their analysis open. In this paper, we propose an End-To-End Deep Neural Network-Hidden Markov Model speech recognition model and a hybrid Connectionist Temporal Classification (CTC)-attention network for the Uzbek language and its dialects. The proposed approach reduces training time and improves speech recognition accuracy by effectively using CTC objective function in attention model training. We evaluated the linguistic and lay-native speaker performances on the Uzbek language dataset, which was collected as a part of this study. Experimental results show that the proposed model achieved a word error rate of 14.3% using 207 h of recordings as an Uzbek language training dataset. Full article

Background: The present study aims to investigate the effect of the first language (L1) orthography on the perception of the second language (L2) vowel contrasts and whether orthographic effects occur at the sublexical level. Methods: Fourteen adult Greek learners of English participated in two AXB discrimination tests: one auditory and one orthography test. In the auditory test, participants listened to triads of auditory stimuli that targeted specific English vowel contrasts embedded in nonsense words and were asked to decide if the middle vowel was the same as the first or the third vowel by clicking on the corresponding labels. The orthography test followed the same procedure as the auditory test, but instead, the two labels contained grapheme representations of the target vowel contrasts. Results: All but one vowel contrast could be more accurately discriminated in the auditory than in the orthography test. The use of nonsense words in the elicitation task eradicated the possibility of a lexical effect of orthography on auditory processing, leaving space for the interpretation of this effect on a sublexical basis, primarily prelexical and secondarily postlexical. Conclusions: L2 auditory processing is subject to L1 orthography influence. Speakers of languages with transparent orthographies such as Greek may rely on the grapheme–phoneme correspondence to decode orthographic representations of sounds coming from languages with an opaque orthographic system such as English. Full article

The Afro-Hispanic creole, Palenquero, has been spoken (together with Spanish) in the village of San Basilio de Palenque, Colombia, for centuries. Until recently, Palenquero was endangered due to prejudice, but language revitalization efforts are underway, and younger speakers are learning Palenquero, but with little reinforcement out of school. The school instruction involves no grammatical explanations, almost no student production, or critical feedback. Adult speakers usually do not address younger speakers in Palenquero, thus leaving school-acquired forms suspended without reinforcement. This represents a unique scenario of heritage acquisition of a language with no bidirectional communication between younger and adult speakers. The present study focuses on the use of preverbal particles and prenominal plural marker by heritage speakers of Palenquero before and after explicit instruction. Communication activities explicitly presented the prenominal plural ma and preverbal particles, such as zero morpheme (simple present), asé (habitual), ta (progressive), a (perfective/simple past) and tan (future). Participants performed better at the post-test and results suggest that explicit explanation of grammatical rules, practice, repetition, and corrective feedback improved the usage of ma and tan. This result lines up with previous studies that posit the amount of time and exposure that learners need in order to acquire complex morphology. Full article

My talk consists of three parts. First, I present the urges and antecedents that are present in the current development of the concept of visuality and can affect education as a considerable development potential. Almost half a century ago something started in education, creating a new learning environment inside and outside the walls of schools by turning static images into dynamic ones. Putting the phenomenon into a conceptional frame, Multimedia Content Development has set new questions and new responses. Owing to the mobile communication tools, Comenius’ Orbis Pictus has become really visible everywhere and at all times in a physical as well as a theoretical-methodological sense, changing by this our learning environment. Recognizing these tendencies, in the second part of my talk, I will deal with what I call the new education dilemmas. The core of these is that e-learning, which shapes everyday learning environments by “ubiquitous computing”, more and more turns away from the traditional or dominant verbal communication, and searches for alternatives by means of which it can be more interesting and more effective for the users. Owing to this situation, serious challenges can be identified with respect to pedagogy. The spontaneous effects of the original human natural characteristics of visual thinking in learning can be considered as an important altering factor in the learning paradigm. The relevant philosophical framework has been there for almost half a century; by now, however, as a result of technological development, it is already generating innovation steps at the practical level. The third part of my talk points to the current search for ways and possibilities, offering not so many solutions, but rather specific examples of investigations and experiments. Instead of suggesting a rigid change of the paradigm I point to the perspective of simply the modalities becoming more complex. In teaching and learning, multimodality—as an attitude which is able to make learning more effective than ever before by means of applying images and signs and rendering the methods of communication significantly more complex—can probably be an important step made forward, leaving behind mechanical, and so rigid, didactical systems. In a modern pedagogical sense, it is highly interesting to examine the notion of modality in terms of teaching and learning in the new technological environment. In its everyday connotation, modality means manner; the speaker’s relation to the coverage of the scope of reality. Considering the special information and knowledge transmitting moments of education, modality means the imparter’s and the recipient’s relation to the content or its coverage of reality. With its earlier centuries-long dominance, the traditional linguistic modality hid the visual modality. Interestingly, the notion of multimodality first appeared in transportation, and so in communication as well, like a “specific method of transportation”, meaning a combined solution including several manners. In linguistic communication, multilingualism, too, means multimodality, and when we are referring to one of the great experiences of our era, i.e., the modality of sign language rich in visual and gestural elements, we are coming closer and closer to the realization that in today’s learning it is precisely multimodal communication that makes us able to transmit knowledge effectively, especially in the cases of disadvantaged groups. In the wake of the 20th century, “modern” learning materials have remained unchanged in terms of verbal and image communication, linear structure, written text dominance, and static image conveyance. Although electronic learning resources and multi-media e-learning representations include more dynamic (flash, podcast, video) transfers of content, the “logic” of building up learning materials has changed little—in fact, visual content is only a complement to verbal communication. But when it comes to community-based learning resource development, teacher training may offer outstandingly good conditions for visual learning. Full article