Alphabetic Languages Research Articles

How the brain encodes morphological constraints during Chinese word reading: An EEG-fNIRS study

Although the role of morphology in alphabetic language processing has been extensively studied, it is still unclear how morphology is enabled and constrained in morpho-syllabic languages like Chinese. This study aims to inspect the time courses and patterns of brain activation associated with Chinese morphological constraint encoding. Chinese native speakers were recruited to perform visual lexical decisions on real Chinese compound words, pseudowords, and nonwords, whilst behavioral, electroencephalographic, and functional near infrared spectroscopy data were simultaneously recorded. For the first time, both morphological and semantic effects were examined to reveal the corresponding spatio-temporal brain activation patterns based on multimodal data. Brain activation differences between pseudowords and real words indexed morphological sensitivity, whereas differences between real words or pseudowords and nonwords characterized semantic effects. Electrophysiological data showed that semantic processing occurred earlier (N400, 300–450 msec) than morphological processing (450–570 msec), while brain activation patterns revealed a differentiation between morphological parsing (specified in the left inferior frontal gyrus) and semantic analysis (in a broader fronto-temporal network). These findings offer new evidence that morphological constraints are encoded at a late stage of compound word processing in Chinese and suggest that the left prefrontal cortex plays an essential role in this process.

Music reading experience modulates eye movement pattern in English reading but not in Chinese reading

Here we tested the hypothesis that in Chinese-English bilinguals, music reading experience may modulate eye movement planning in reading English but not Chinese sentences due to the similarity in perceptual demands on processing sequential symbol strings separated by spaces between music notation and English sentence reading. Chinese–English bilingual musicians and non-musicians read legal, semantically incorrect, and syntactically (and semantically) incorrect sentences in both English and Chinese. In English reading, musicians showed more dispersed eye movement patterns in reading syntactically incorrect sentences than legal sentences, whereas non-musicians did not. This effect was not observed in Chinese reading. Musicians also had shorter saccade lengths when viewing syntactically incorrect than correct musical notations and sentences in an unfamiliar alphabetic language (Tibetan), whereas non-musicians did not. Thus, musicians’ eye movement planning was disturbed by syntactic violations in both music and English reading but not in Chinese reading, and this effect was generalized to an unfamiliar alphabetic language. These results suggested that music reading experience may modulate perceptual processes in reading differentially in bilinguals’ two languages, depending on their processing similarities.

Sign Language Recognition System

Abstract: A large number of deaf and mute people are present around the world and communicating with them is a bit difficult at times; because not everyone can understand Sign language(a system of communication using visual gestures and signs). In addition, there is a lack of official sign language interpreters. In India, the official number of approved sign language interpreters is only 250[1] . This makes communication with deaf and mute people very difficult. The majority of deaf and dumb teaching methods involve accommodating them to people who do not have disabilities - while discouraging the use of sign language. There is a need to encourage the use of sign language. People communicate with each other in sign language by using hand and finger gestures. The language serves its purpose by bridging the gap between the deaf-mute and speaking communities. With recent technological developments, sign language identification is a hard subject in the field of computer vision that has room for further progress. In this project, we propose an optimal recognition engine whose main objective is to translate static American Sign Language alphabets, numbers, and words into human and machine understandable English script and the other way around. Using Neural Networks, we offer a machine learning-based technique for identifying American Sign Language. Keywords: deep learning; convolutional neural network; recognition; comparison; sign language;

COMPUTER WORD RECOGNITION- IMAGE PROCESSING USING SIGN GESTURES- CREATION OF A NOVEL SIGN LANGUAGE

Sign language is used by deaf and hard hearing people to exchange information between their own community and other people. Computer recognition of Sign language deals from Sign gesture acquisition and continues till text/speech generation. Sign gestures can be classified as static and dynamic. However static gesture recognition is simpler than dynamic gesture recognition but both recognition systems are important to the human community. However, most people do not know the sign language. In this project, we aim to automatically recognize sign language Alphabet / Numbers / Words in image- based methodology using MATLAB. The problem addressed is based on Digital Image Processing using Skin Detection, Image Segmentation, Image Filtering, and cross- correlation method. This system expects to achieve recognizing gestures of ISL (Indian Sign Language) by special people and converting into speech/text. The statistic of the result of the implementation, it is therefore concluded that the method is used for cross-correlation and color segmentation work with hand gesture recognition. The results obtained are applicable and can be implemented in a mobile device smart phone having a frontal camera. The vision of an efficient system to translate sign language to text is quite achievable, but the challenges lie in optimization. Key Words: Computer recognition, Skin Detection, ISL (Indian Sign Language)

Sign Language Recognition and Interpretation System

Sign language is a visual language that individuals with speech and hearing difficulties use to communicate in their daily conversations. Through its original grammar, it is totallyan optical communication language, as opposed to vocal languages. This study report proposed an effective strategy to accomplishing the translation of 24 static sign language alphabets and numerals of American Sign Language into humanoid. Researchers are now focusing their efforts on building commercially viable Sign Language Recognition systems. Researchers use a range of techniques to perform their research. It all starts with the methods of data acquisition. The data collection method varies depending on the cost of a suitable device, however for the Sign Language Recognition System to be commercialized, a low-cost strategy is required. The methods used by researchers to develop Sign Language Recognition varied as well. Each approach has its own advantages over others, and researchers are continually experimenting with various methods to produce their own Sign Language Recognition. Each approach has its own set of limitations when compared to others. The purpose of this study is to examine several ways to sign language recognitionand choose the optimal method. Keywords — Feature Extraction and Representation, Artificial Neural Networks, Convolution Neural Network, TensorFlow, Keras, OpenCV.

The Brain Connectome for Chinese Reading.

Chinese, as a logographic language, fundamentally differs from alphabetic languages like English. Previous neuroimaging studies have mainly focused on alphabetic languages, while the exploration of Chinese reading is still an emerging and fast-growing research field. Recently, a growing number of neuroimaging studies have explored the neural circuit of Chinese reading. Here, we summarize previous research on Chinese reading from a connectomic perspective. Converging evidence indicates that the left middle frontal gyrus is a specialized hub region that connects the ventral with dorsal pathways for Chinese reading. Notably, the orthography-to-phonology and orthography-to-semantics mapping, mainly processed in the ventral pathway, are more specific during Chinese reading. Besides, in addition to the left-lateralized language-related regions, reading pathways in the right hemisphere also play an important role in Chinese reading. Throughout, we comprehensively review prior findings and emphasize several challenging issues to be explored in future work.

Neural representation of phonological information during Chinese character reading.

Previous studies have revealed that phonological processing of Chinese characters elicited activation in the left prefrontal cortex, bilateral parietal cortex, and occipitotemporal regions. However, it is controversial what role the left middle frontal gyrus plays in Chinese character reading, and whether the core regions (e.g., the left superior temporal gyrus and supramarginal gyrus) for phonological processing of alphabetic languages are also involved in Chinese character reading. To address these questions, the present study used both univariate and multivariate analysis (i.e., representational similarity analysis, RSA) to explore neural representations of phonological information during Chinese character reading. Participants were scanned while performing a reading aloud task. Univariate activation analysis revealed a widely distributed network for word reading, including the bilateral inferior frontal gyrus, middle frontal gyrus, lateral temporal cortex, and occipitotemporal cortex. More importantly, RSA showed that the left prefrontal (i.e., the left middle frontal gyrus and left inferior frontal gyrus) and bilateral occipitotemporal areas (i.e., the left inferior and middle temporal gyrus and bilateral fusiform gyrus) represented phonological information of Chinese characters. These results confirmed the importance of the left middle frontal gyrus and regions in ventral pathway in representing phonological information of Chinese characters.

Increasing intercharacter spacing reduces the transposed-character effect in Chinese reading: Evidence from eye movements

ABSTRACT Spacing is a very important visual cue in alphabetic languages as well as other languages, such as Chinese, which has no special interword spacing but has equal intercharacter spacing. Studies have shown that spacing has a significant effect on letter/character identity or position processing. However, whether spacing modulates the transposed-letter/-character effect remains unknown. This study conducted an eye-movement experiment using the boundary paradigm to explore whether increasing intercharacter spacing affected the transposed-character effect in Chinese reading. The results indicate that Chinese readers have flexible adjustment strategies for intercharacter spacing and that there is an obvious transposed-character effect. Crucially, increasing intercharacter spacing by three points resulted in stricter character position processing as compared with identity processing, thus reducing the transposed-character effect. Our findings are consistent with models in which visual elements comprise an important factor in the transposed-letter/-character effect, while the existence of the transposed-character effect suggests that the orthographic abstract component is also relevant.

Functional Gradient of the Fusiform Cortex for Chinese Character Recognition

Visual word recognition has been proposed to have a functional and spatial organization corresponding to hierarchical language-like word forms in the left fusiform gyrus (FG) during visual word recognition in alphabetic languages. However, it is still unclear whether the similar functional gradients of word-like representation exist during Chinese character recognition. In this study, we adopted univariate activation analysis and representational similarity analysis (RSA) methods to investigate the functional organization in the FG for Chinese character recognition using task fMRI data. Native Chinese readers were visually presented with four types of character-like stimuli (i.e., real characters, pseudo-characters, false characters, and stroke combinations). After analysis, we observed a posterior-to-anterior functional gradient in the left FG corresponding to the degree of likeness of stimuli to character. Additionally, distinct subregions of the left FG harbor different orthographic codes. The middle part of the left FG was involved in abstract orthographic processing, while the anterior part of the left FG was involved in lexical orthographic processing (i.e., mapping orthography onto phonology or semantics). Notably, for the right FG, we did not find similar coding pattern for selectivity to character likeness, indicating the asymmetry of the functional hierarchical organization in favor of the left hemisphere. In conclusion, our findings revealed that the left FG presents a posterior-to-anterior gradient functional processing for Chinese character recognition, which expands our understanding of the psychological, neural, and computational theories of word reading.

Increased Gray Matter Volume Induced by Chinese Language Acquisition in Adult Alphabetic Language Speakers.

It is interesting to explore the effects of second language (L2) acquisition on anatomical change in brain at different stages for the neural structural adaptations are dynamic. Short-term Chinese training effects on brain anatomical structures in alphabetic language speakers have been already studied. However, little is known about the adaptations of the gray matter induced by acquiring Chinese language for a relatively long learning period in adult alphabetic language speakers. To explore this issue, we recruited 38 Indian overseas students in China as our subjects. The learned group included 17 participants who had learned Mandarin Chinese for an average of 3.24 years and achieved intermediate Chinese language proficiency. The control group included 21 subjects who had no knowledge about Chinese. None of the participants had any experience in learning logographic and tonal language before Chinese learning. We found that (1) the learned group had significantly greater gray matter volume (GMV) in the left lingual gyrus (LG) compared with the control group; (2) the Chinese characters’ reading accuracy was significantly and positively correlated to the GMV in the left LG and fusiform gyrus (FG) across the two groups; and (3) in the learned group, the duration of Chinese learning was significantly and positively correlated with the GMV in the left inferior frontal gyrus (IFG) after correction for multiple comparisons with small volume corrections. Our structural imaging findings are in line with the functional imaging studies reporting increased brain activation induced by Chinese acquisition in alphabetic language speakers. The regional gray matter changes reflected the additional requirements imposed by the more difficult processing of Chinese characters and tones. The present study also show that the biological bases of the adaptations induced by a relatively long period of Chinese learning were limited in the common areas for first and foreign language processing.

Sign Language Recognition for Arabic Alphabets Using Transfer Learning Technique.

Sign language is essential for deaf and mute people to communicate with normal people and themselves. As ordinary people tend to ignore the importance of sign language, which is the mere source of communication for the deaf and the mute communities. These people are facing significant downfalls in their lives because of these disabilities or impairments leading to unemployment, severe depression, and several other symptoms. One of the services they are using for communication is the sign language interpreters. But hiring these interpreters is very costly, and therefore, a cheap solution is required for resolving this issue. Therefore, a system has been developed that will use the visual hand dataset based on an Arabic Sign Language and interpret this visual data in textual information. The dataset used consists of 54049 images of Arabic sign language alphabets consisting of 1500\\ images per class, and each class represents a different meaning by its hand gesture or sign. Various preprocessing and data augmentation techniques have been applied to the images. The experiments have been performed using various pretrained models on the given dataset. Most of them performed pretty normally and in the final stage, the EfficientNetB4 model has been considered the best fit for the case. Considering the complexity of the dataset, models other than EfficientNetB4 do not perform well due to their lightweight architecture. EfficientNetB4 is a heavy-weight architecture that possesses more complexities comparatively. The best model is exposed with a training accuracy of 98 percent and a testing accuracy of 95 percent.

BenSignNet: Bengali Sign Language Alphabet Recognition Using Concatenated Segmentation and Convolutional Neural Network

Sign language recognition is one of the most challenging applications in machine learning and human-computer interaction. Many researchers have developed classification models for different sign languages such as English, Arabic, Japanese, and Bengali; however, no significant research has been done on the general-shape performance for different datasets. Most research work has achieved satisfactory performance with a small dataset. These models may fail to replicate the same performance for evaluating different and larger datasets. In this context, this paper proposes a novel method for recognizing Bengali sign language (BSL) alphabets to overcome the issue of generalization. The proposed method has been evaluated with three benchmark datasets such as ‘38 BdSL’, ‘KU-BdSL’, and ‘Ishara-Lipi’. Here, three steps are followed to achieve the goal: segmentation, augmentation, and Convolutional neural network (CNN) based classification. Firstly, a concatenated segmentation approach with YCbCr, HSV and watershed algorithm was designed to accurately identify gesture signs. Secondly, seven image augmentation techniques are selected to increase the training data size without changing the semantic meaning. Finally, the CNN-based model called BenSignNet was applied to extract the features and classify purposes. The performance accuracy of the model achieved 94.00%, 99.60%, and 99.60% for the BdSL Alphabet, KU-BdSL, and Ishara-Lipi datasets, respectively. Experimental findings confirmed that our proposed method achieved a higher recognition rate than the conventional ones and accomplished a generalization property in all datasets for the BSL domain.

A design approach for a distributed system to handle Chinese

In designing systems to handle non-Roman alphabet languages, unique problems in information retrieval are encountered. The concept of "P-trees” will be explained and compared to B-trees. Experiences in applying P-trees to non-Roman alphabet retrieval environments will be covered in detail.

Jaipreet Virdi, Hearing Happiness: Deafness Cures in History

“Deaf peddling” refers to the practice by deaf individuals — or hearing people feigning deafness — of selling sign language alphabet cards or other sundries to sympathetic hearing folks in mall food courts or airports. In the medical realm, however, it might instead denote the peddling of “cures” to individuals anxious to restore their hearing. In her groundbreaking work Hearing Happiness: Deafness Cures in History, Jaipreet Virdi examines over two centuries’ worth of devices, potions, rituals, and surgeries marketed as panaceas for hearing loss. Virdi combines extensive historical research with personal memoir, poignantly recounting her own experience with deafness. She weaves together newspaper and magazine advertisements, professional and lay medical journals, her own material interaction with various devices, and accounts by deaf and hard-of-hearing individuals themselves to argue that while the demarcations between quack cures and legitimate treatments have been — and still remain — obscure, the pursuit of...

The tip-of-the-Mandarin tongue: phonological and orthographic priming of TOT resolution in Mandarin speakers

ABSTRACT Studies of tip-of-the-tongue (TOT) experiences in English have shown that priming the TOT’s first syllable, especially a low-frequency one, helps to resolve the TOT. We explored whether priming of TOT resolution occurs in Mandarin, a language whose visual representation (orthography) is largely independent of sound (phonology). Participants saw descriptions corresponding to cheng-yu targets, four-character Chinese idioms. After a TOT, they saw a list of words where one was sometimes a phonological (Experiment 1) or orthographic (Experiment 2) prime. Phonological primes had a first character different from the target’s but contained either its first syllable or first phoneme, whereas orthographic primes contained the target’s first radical. Results showed that two factors marginally increased TOT resolution: first syllable primes and higher-frequency first radicals. These results are discussed in terms of a transmission deficit model of TOTs in Mandarin where priming of TOT resolution has both similarities and differences with alphabetic languages.

An Instrumented Glove for Recognition of Brazilian Sign Language Alphabet

This paper presents the development and analysis of a system for Brazilian Sign Language (Libras) recognition, which is composed of an instrumented glove and an acquisition system. The instrumented glove has five flex sensors, an inertial sensor, and two contact sensors (made with silver-coated fabric). For data acquisition, five volunteers performed gestures in Libras. In the proposed segmentation technique, the collected data were segmented into three periods (fixed amounts of signal samples): construction period, alphabet gesture, and relaxation period. The periods of alphabet gesture are submitted to segmentation, and the classifier was designed to recognize the 26 letters of alphabet. Different classifiers were employed to classify the gestures and analyze the system in different scenarios. For the classification in group of sensors, the highest performance obtained was an accuracy of 96.15% with Random Forest (RF) classifier.

Atypical Relationships Between Neurofunctional Features of Print-Sound Integration and Reading Abilities in Chinese Children With Dyslexia.

Conquering print-sound mappings (e.g., grapheme-phoneme correspondence rules) is vital for developing fluent reading skills. In neuroimaging research, this ability can be indexed by activation differences between audiovisual congruent against incongruent conditions in brain areas such as the left superior temporal cortex. In line with it, individuals with dyslexia have difficulty in tasks requiring print-sound processing, accompanied by a reduced neural integration. However, existing evidence is almost restricted to alphabetic languages. Whether and how multisensory processing of print and sound is impaired in Chinese dyslexia remains underexplored. In this study, we applied a passive audiovisual integration paradigm with functional magnetic resonance imaging to investigate the possible dysfunctions in processing character-sound (opaque; semantics can be automatically accessed) and pinyin-sound associations (transparent; no particular meaning can be confirmed) in Chinese dyslexic children. Unexpectedly, the dyslexic group did not show reduced neural integration compared with typically developing readers in either character or pinyin experiment. However, the results revealed atypical correlations between neural integration and different reading abilities in dyslexia. Specifically, while the neural integration in the left inferior frontal cortex in processing character-sound pairs correlated with silent reading comprehension in both children with and without dyslexia, it was associated with morphological awareness (semantic-related) in controls but with rapid naming (phonological-related) in dyslexics. This result indicates Chinese dyslexic children may not use the same grapho-semantic processing strategy as their typical peers do. As for pinyin-sound processing, while a stronger neural integration in the direction of “congruent > incongruent” in the left occipito-temporal cortex and bilateral superior temporal cortices was associated with better oral reading fluency in the control group, an opposite pattern was found in dyslexia. This finding may reflect dyslexia's dysfunctional recruitment of the regions in grapho-phonological processing, which further impedes character learning.

Indian sign language alphabet recognition system using CNN with diffGrad optimizer and stochastic pooling

Indian sign language alphabet recognition system using CNN with diffGrad optimizer and stochastic pooling

Multiple Communication Channels in Literary Texts

The statistical theory of language translation is used to compare how a literary character speaks to different audiences by diversifying two important linguistic communication channels: the “sentences channel” and the “interpunctions channel”. The theory can “measure” how the author shapes a character speaking to different audiences, by modulating deep-language parameters. To show its power, we have applied the theory to the literary corpus of Maria Valtorta, an Italian mystic of the XX-century. The likeness index , ranging from 0 to 1, allows to “measure” how two linguistic channels are similar, therefore implying that a character speaks to different audiences in the same way. A 6-dB difference between the signal-to-noise ratios of two channels already gives IL ≈ 0.5, a threshold below which the two channels depend very little on each other, therefore implying that the character addresses different audiences differently. In conclusion, multiple linguistic channels can describe the “fine tuning” that a literary author uses to diversify characters or distinguish the behavior of the same character in different situations. The theory can be applied to literary corpora written in any alphabetical language.

From the History of Latinization in Karakalpakstan for the Years of Independence

In the article, at the beginning of 1990s in Independent Uzbekistan began work on transferring the records of the population of this country to the Latin alphabet. At the end of 1993, the project of the Latin alphabet was approved. According to this Charter, the gradual transition of the new national Uzbek Alphabet began on September 1, 1995, and the tasks for its full completion were defined until 2000. In the conditions of Uzbekistan, the alphabet was approved, the spelling plan was developed, on the basis of which new textbooks and educational tools for the 1st classes of preschool institutions and schools were prepared and published. In the preparation of the Karakalpak alphabet based on Latin script in Karakalpakstan, a working group consisting of scientists, methodists, teachers was actively working in the terminology Department under the Council of Ministers of the Republic of Karakalpakstan and as a result, in February 1994 a new alphabet of Karakalpak language was approved. Also, amendments and additions were introduced to the regulations adopted in September 1994 and the alphabet consisted of 32 letters. In 1995, Uzbek and a little later Karakalpak alphabet was revised. The terminology consists of 8 specialists, the alphabet has been improved by introducing changes and additions depending on the sound of the letters of the accepted alphabet. According to the law of October 8, 2009, some letters were replaced. In order to re-examine the alphabet of Karakalpakstan based on Latin script by the Jokargy Kenges of the Republic of Karakalpakstan, the relevant commission was formed. This issue was studied by the commission and some changes were made in order to improve the Latin alphabet and spelling rules of the new spruce. In 2016, the next reform of the Karakalpak alphabet was carried out. The reform of 2009 year abolished the rules on the spelling of certain letters.