Braille Words Research Articles

Enhancing Chinese–Braille translation: A two-part approach with token prediction and segmentation labeling

Visually assistive systems for the visually impaired play a pivotal role in enhancing the quality of life for the visually impaired. Assistive technologies for the visually impaired have undergone a remarkable transformation with the advent of deep learning and sophisticated assistive devices. In particular, the paper utilizes the latest machine translation models and techniques to accomplish the Chinese–Braille translation task, providing convenience for visually impaired individuals. The Traditional end-to-end Chinese–Braille translation approach incorporates Braille dots and Braille word segmentation symbols as tokens within the model’s vocabulary. However, our findings reveal that Braille word segmentation is significantly more complex than Braille dot prediction. The paper proposes a novel Two-Part Loss (TPL) method that treats these tasks distinctly, leading to significant accuracy improvements. To enhance translation performance further, we introduce a BERT-Enhanced Segmentation Transformer (BEST) method. BEST leverages knowledge distillation techniques to transfer knowledge from a pre-trained BERT model to the translate model, mitigating its limitations in word segmentation. Additionally, soft label distillation is employed to improve overall efficacy further. The TPL approach achieves an average BLEU score improvement of 1.16 and 5.42 for Transformer and GPT models on four datasets, respectively. In addition, The work presents a two-stage deep learning-based translation approach that outperforms traditional multi-step and end-to-end methods. The proposed two-stage translation method achieves an average BLEU score improvement of 0.85 across four datasets.

Japanese Braille Translation Using Deep Learning - Conversion from Phonetic Characters (Kana) to Homonymic Characters (Kanji).

A blind student writes and submits reports in Braille word processor, which is difficult for teachers to read. This study's purpose is to make a translator from Braille into mixed Kana-Kanji sentences for such teachers. Because Kanji has homonyms, it is not always possible to get correct results when converting. To overcome this difficulty, we used deep learning for translation. We built a training dataset composed from 15,000 pairs of Braille codes and mixed Kana-Kanji sentences, and a validation dataset. In training, we got an accuracy of 0.906 and a good Bleu score of 0.600. In validation, we found 5 mistaken words in selecting homonymous Kanji by examining translation mistakes from 100 pairs of the verification sentences. The choice of homonymous Kanji depends on the context. For decreasing such type of errors, it is necessary to introduce of translation of paragraphs by increasing the scale of the network model in deep learning, and to expand the network structure.

Letter-similarity effects in braille word recognition.

Letter-similarity effects are elusive with common words in lexical decision experiments: viotin and viocin (base word: violin) produce similar error rates and rejection latencies. However, they are robust for stimuli often presented with the same appearance (e.g., misspelled logotypes such as anazon [base word: amazon] produce more errors and longer latencies than atazon). Here, we examine whether letter-similarity effects occur in reading braille. The rationale is that braille is a writing system in which the sensory information is processed in qualitatively different ways than in visual reading: the form of the word's letters is highly stable due to the standardisation of braille and the sensing of characters is transient and somewhat serial. Hence, we hypothesised that the letter similarity effect would be sizable with misspelled common words in braille, unlike the visual modality. To test this hypothesis, we conducted a lexical decision experiment with blind adult braille readers. Pseudowords were created by replacing one letter of a word with a tactually similar or dissimilar letter in braille following a tactile similarity matrix (e.g., [ausor] vs [aucor]; baseword: [autor]). Bayesian linear mixed-effects models showed that the responses to tactually similar pseudowords were less accurate than to tactually dissimilar pseudowords-the response times (RTs) showed a parallel trend. This finding supports the idea that, when reading braille, the mapping of input information onto abstract letter representations is done through a noisy channel.

Braille literacy as a human right: Achallengetothe"inefficiency" argument against braille instruction.

The United Nations Convention on the Rights of Persons with Disabilities (CRPD) affirms a right to education for disabled persons and aims to ensure braille instruction for blind individuals. However, there is evidence that braille instruction is often circumvented or abandoned early in CRPD nations because it is perceived as an inefficient learning medium for blind students. This perception persists despite insufficient empirical evidence and a lack of understanding of the efficiency of reading versus listening for learning in sighted individuals. We therefore investigated the efficiency of learning written versus spoken words in blind and sighted samples. Participants (23 blind, 20 sighted) studied the written definitions of 70 rare English words in successive rounds, presented in conjunction with written or spoken wordforms. Blind participants learned with equal efficiency across modalities, whereas sighted participants learned spoken words more efficiently. The findings indicate the inefficiency argument against teaching braille is groundless, both because braille word learning is not less efficient than auditory word learning for blind individuals, and because reading is valued in the education of sighted individuals despite its apparent inefficiency in that population.

Design and Implementation of Chinese Common Braille Translation System Integrating Braille Word Segmentation and Concatenation Rules.

An important sign of the accessibility of Braille information is the realization of the mutual translation between Chinese and the Braille. Due to the irregularity and uncertainty of the Prevailing Mandarin Braille, coupled with the lack of a large-scale Braille corpus, the quality of Chinese-Braille translation seems to be poor. In July 2018, the National Language Commission released the “Chinese Common Braille Scheme” and advocated replacing the “Prevailing Mandarin Braille.” Aimed at improving translation accuracy, this research, which is based on the self-built Chinese Common Braille corpus and combined with the HanLP (Han Language Processing) dictionary and the Chinese-Braille word corpus (a Braille word segmentation and concatenation dictionary for generating a unigram language model), uses the n-gram language model to design and implement a Chinese-Braille intertranslation system that integrates Chinese and Braille Word Segmentation and Concatenation Rules. More importantly, this research proposes an experimental plan for improving the Braille Word Segmentation and Concatenation Rules using a Chinese-Braille word corpus. Experiments show that in the field of educational literature, the accuracy rate of translation from Chinese to Chinese Common Braille has reached 95.01%, and the accuracy of Chinese Common Braille to Chinese translation has reached 90.15%.

Creating Tactile Educational Materials for the Visually Impaired and Blind Students Using AI Cloud Computing

There are 24.5 million visually impaired and blind (VIB) students who have limited access to educational materials due to cost or availability. Although advancement in technology is prevalent, providing individualized learning using technology remains a challenge without the proper tools or experience. The TacPic system was developed as an online platform to create tactile educational materials (TEM) based on the image inputs of users who do not have prior experience in tactile photo development or 3D printing. The TacPic system allows the users to simply upload images to a website and uses AI cloud computing on the Amazon Web Services platform. First, it segments and labels the images. Then, the text label is converted into braille words. Subsequently, surface rendering and consolidation of the image and text is performed, before it is converted into a single file that is ready for 3D printing. Currently, the types of TEM that can be created are tactile flashcards, tactile maps, and tactile peg puzzles, which can be developed within a few hours. This is in contrast to a development period of weeks using traditional methods. Furthermore, the tactile educational materials were tested by two VIB teachers and six VIB students. It was found that those who are congenitally blind need more time to identify the object and rely more on the braille labels compared to students who became blind at a later age. Teachers also suggested producing TEM that use simpler images, and TEM that are suitable for both sighted and VIB students. In conclusion, the researchers successfully developed a platform that allows more educators or parents to develop personalized and individualized TEM. In the future, further optimization of the algorithms to improve segmentation and the inclusion of other features, such as color, could be undertaken. Finally, new printing materials and methods are needed to improve printing efficiency.

Using e-mail as performance feedback to teach paraprofessionals to implement constant time delay with braille words

Equipping paraprofessionals to implement evidence-based instructional practices with fidelity can enhance the education of students with visual impairments. We used a multiple probe across participants design to evaluate the ability of paraprofessionals to follow constant time delay procedures with high fidelity when teaching braille words. We delivered performance feedback by e-mail and examined student learning outcomes. All three paraprofessionals achieved 100% correct implementation of constant time delay and maintained this high level of implementation over time. All three students successfully learned the targeted words. The combination of the training and support with e-mail feedback was effective at equipping them to deliver an evidence-based practice. Paraprofessionals affirmed the social validity of the intervention and considered e-mail performance feedback as an easy-to-understand way of receiving much-needed guidance. E-mail feedback is a cost-effective and simple tool for providing constructive feedback, while also ensuring paraprofessionals deliver instruction with high fidelity.

Temporal Dynamics of Brain White Matter Plasticity in Sighted Subjects during Tactile Braille Learning: A Longitudinal Diffusion Tensor Imaging Study.

The white matter (WM) architecture of the human brain changes in response to training, though fine-grained temporal characteristics of training-induced white matter plasticity remain unexplored. We investigated white matter microstructural changes using diffusion tensor imaging at five different time points in 26 sighted female adults during 8 months of training on tactile braille reading. Our results show that training-induced white matter plasticity occurs both within and beyond the trained sensory modality, as reflected by fractional anisotropy (FA) increases in somatosensory and visual cortex, respectively. The observed changes followed distinct time courses, with gradual linear FA increase along the training in the somatosensory cortex and sudden visual cortex cross-modal plasticity occurring after braille input became linguistically meaningful. WM changes observed in these areas returned to baseline after the cessation of learning in line with the supply-demand model of plasticity. These results also indicate that the temporal dynamics of microstructural plasticity in different cortical regions might be modulated by the nature of computational demands. We provide additional evidence that observed FA training-induced changes are behaviorally relevant to tactile reading. Together, these results demonstrate that WM plasticity is a highly dynamic process modulated by the introduction of novel experiences.SIGNIFICANCE STATEMENT Throughout the lifetime the human brain is shaped by various experiences. Training-induced reorganization in white matter (WM) microstructure has been reported, but we know little about its temporal dynamics. To fill this gap, we scanned sighted subjects five times during tactile braille reading training. We observed different dynamics of WM plasticity in the somatosensory and visual cortices implicated in braille reading. The former showed a continuous increase in WM tissue anisotropy along with tactile training, while microstructural changes in the latter were observed only after the participants learned to read braille words. Our results confirm the supply-demand model of brain plasticity and provide evidence that WM reorganization depends on distinct computational demands and functional roles of regions involved in the trained skill.

Fittle: A Novel Braille Toy.

Toys for children with visual impairment and blindness are very limited. We have developed a three-dimensional (3D)-printed Braille puzzle with a potential for educational use. This article describes the development of a novel Braille toy using 3D printing technology that potentially could be used for teaching Braille for children with blindness and/or profound visual impairment. Fittle is a 3D-printed puzzle with embossed Braille letters. Upon correct fitting of the puzzle, one not only can spell the Braille word but also would be able to feel the contour of the representative object that the word denotes. A smartphone application (Sound of Fittle) was developed to be used in conjunction with Fittle. A pilot testing was done on participants with vision impairment. Time taken to solve the puzzle and/or identify the Braille letters was calculated. Three Fittle puzzles were tested. Instructions to solve the puzzle were given only after the first attempt. Seven participants (one adult and six children) were recruited. The mean time taken for the first attempt was longer (4.5 minutes), and upon instructions, the time taken to solve the puzzle was reduced on an average by a factor of 2.5. All the subjects were able to fit and read the embossed Braille in the Fittle. Fittle is a novel Braille toy made using 3D printing technology. Fittle can potentially be used as an educational toy. The Sound of Fittle application gives the experiential sound for the associated word. The designs for the Fittle and the application are made available as open source on the Internet. Anyone with an access to a 3D printer can print, produce, and use the Fittle for free. With instructions, an individual can quickly learn to solve and play with the puzzle.

Chinese to Braille translation based on Braille word segmentation using statistical model

Automatic translation of Chinese text to Chinese Braille is important for blind people in China to acquire information using computers or smart phones. In this paper, a novel scheme of Chinese-Braille translation is proposed. Under the scheme, a Braille word segmentation model based on statistical machine learning is trained on a Braille corpus, and Braille word segmentation is carried out using the statistical model directly without the stage of Chinese word segmentation. This method avoids establishing rules concerning syntactic and semantic information and uses statistical model to learn the rules stealthily and automatically. To further improve the performance, an algorithm of fusing the results of Chinese word segmentation and Braille word segmentation is also proposed. Our results show that the proposed method achieves accuracy of 92.81% for Braille word segmentation and considerably outperforms current approaches using the segmentation-merging scheme.

Braille in the Sighted: Teaching Tactile Reading to Sighted Adults.

Blind people are known to have superior perceptual abilities in their remaining senses. Several studies suggest that these enhancements are dependent on the specific experience of blind individuals, who use those remaining senses more than sighted subjects. In line with this view, sighted subjects, when trained, are able to significantly progress in relatively simple tactile tasks. However, the case of complex tactile tasks is less obvious, as some studies suggest that visual deprivation itself could confer large advantages in learning them. It remains unclear to what extent those complex skills, such as braille reading, can be learnt by sighted subjects. Here we enrolled twenty-nine sighted adults, mostly braille teachers and educators, in a 9-month braille reading course. At the beginning of the course, all subjects were naive in tactile braille reading. After the course, almost all were able to read whole braille words at a mean speed of 6 words-per-minute. Subjects with low tactile acuity did not differ significantly in braille reading speed from the rest of the group, indicating that low tactile acuity is not a limiting factor for learning braille, at least at this early stage of learning. Our study shows that most sighted adults can learn whole-word braille reading, given the right method and a considerable amount of motivation. The adult sensorimotor system can thus adapt, to some level, to very complex tactile tasks without visual deprivation. The pace of learning in our group was comparable to congenitally and early blind children learning braille in primary school, which suggests that the blind’s mastery of complex tactile tasks can, to a large extent, be explained by experience-dependent mechanisms.

Chinese-Braille Translation Based on Braille Corpus

For people with visual disabilities, reading Braille text is an important way to acquire information. There are great challenges for Chinese-Braille translation due to the characteristics of word segmentation and tone marking in Chinese Braille. In this paper, a novel scheme of Chinese-Braille translation is proposed. Unlike current methods which use heuristic rules defined by experts for Braille word segmentation, the proposed method performs Chinese-Braille translation based on a Braille Corpus without experts on Braille. Under the scheme, a Braille word segmentation model based on statistical machine learning is trained on a Braille corpus, and Braille word segmentation is carried out using the statistical model directly without the stage of Chinese word segmentation. Tone marking and some special treatment are also performed based on word and rule mining on the Corpus. This method avoids manually establishment of rules concerning syntactic and semantic information and uses statistical model to learn the rules by stealthily and automatically. Experimental results show the effectiveness of the proposed approach.

Using Constant Time Delay to Teach Braille Word Recognition

Introduction Constant time delay has been identified as an evidence-based practice to teach print sight words and picture recognition (Browder, Ahlbrim-Delzell, Spooner, Mims, & Baker, 2009). For the study presented here, we tested the effectiveness of constant time delay to teach new braille words. Methods A single-subject multiple baseline across behaviors design was used to investigate the use of constant time delay to teach recognition of highly motivating braille words to four students with visual impairments and intellectual disabilities. Results Each participant learned all words taught (9–12 words each). A functional relation was demonstrated for all four participants by immediate changes in trend from baseline to intervention. Discussion This is the first published report of the successful use of constant time delay to teach braille word recognition to students with visual impairments and intellectual disabilities. An attending cue was introduced into the procedures for students with a low number of unprompted correct responses, and results were positive. Possible sources of variability in word retention are discussed. Implications for practitioners Results suggest constant time delay can be adapted and implemented with braille readers in typical teaching environments.

Letter Position Coding Across Modalities: The Case of Braille Readers

BackgroundThe question of how the brain encodes letter position in written words has attracted increasing attention in recent years. A number of models have recently been proposed to accommodate the fact that transposed-letter stimuli like jugde or caniso are perceptually very close to their base words.MethodologyHere we examined how letter position coding is attained in the tactile modality via Braille reading. The idea is that Braille word recognition may provide more serial processing than the visual modality, and this may produce differences in the input coding schemes employed to encode letters in written words. To that end, we conducted a lexical decision experiment with adult Braille readers in which the pseudowords were created by transposing/replacing two letters.Principal FindingsWe found a word-frequency effect for words. In addition, unlike parallel experiments in the visual modality, we failed to find any clear signs of transposed-letter confusability effects. This dissociation highlights the differences between modalities.ConclusionsThe present data argue against models of letter position coding that assume that transposed-letter effects (in the visual modality) occur at a relatively late, abstract locus.

Design of Braille Display System Based on Piezoelectric Actuator Array

According to the situation that conditional Braille book is difficulty in publication and its amount is small. This paper puts forward a tactile display system which can transform content of common e-book to Braille information, and the blind comprehend the text by touching the Braille formed by the tactile display device. This Braille tactile display system extracts Chinese characters by OCR technology. The text recognized is segmented into word blocks according to the rule of Braille word segmentation before transforming to double-phoneme mandarin Braille. It uses dsPIC30F2010 to receive Braille signal and then controls the piezoelectric actuator array to output corresponding displacement.

Organization and Reorganization of Sensory-Deprived Cortex

The scientific literature has grown rich in research illustrating the remarkable ability of the brain to reorganize itself following sensory loss. In particular, visually deafferented regions within the occipital cortex of early blind individuals have been repeatedly shown to be functionally recruited to carry out a wide variety of nonvisual tasks. While the novelty of such a finding might be wearing off, more recent research has begun to examine whether this crossmodal takeover of the occipital cortex in blindness follows some sort of organizational principle. Here we first review the most recent evidence from neuroimaging studies that illustrate how the pre-existing functional specialization of cortical sub-regions appears to be preserved following sensory deprivation. We discuss and compare work on visual and auditory deprivation, as well as research on individuals with intact sensory systems. We suggest avenues for future exploration of these issues, such as identifying the neuroanatomical markers of crossmodal plasticity and elucidating the behavioral relevance of observed changes.

Recognition memory for Braille or spoken words: An fMRI study in early blind

We examined cortical activity in early blind during word recognition memory. Nine participants were blind at birth and one by 1.5years. In an event-related design, we studied blood oxygen level-dependent responses to studied (“old”) compared to novel (“new”) words. Presentation mode was in Braille or spoken. Responses were larger for identified “new” words read with Braille in bilateral lower and higher tier visual areas and primary somatosensory cortex. Responses to spoken “new” words were larger in bilateral primary and accessory auditory cortex. Auditory cortex was unresponsive to Braille words and occipital cortex responded to spoken words but not differentially with “old”/“new” recognition. Left dorsolateral prefrontal cortex had larger responses to “old” words only with Braille. Larger occipital cortex responses to “new” Braille words suggested verbal memory based on the mechanism of recollection. A previous report in sighted noted larger responses for “new” words studied in association with pictures that created a distinctiveness heuristic source factor which enhanced recollection during remembering. Prior behavioral studies in early blind noted an exceptional ability to recall words. Utilization of this skill by participants in the current study possibly engendered recollection that augmented remembering “old” words. A larger response when identifying “new” words possibly resulted from exhaustive recollecting the sensory properties of “old” words in modality appropriate sensory cortices. The uniqueness of a memory role for occipital cortex is in its cross-modal responses to coding tactile properties of Braille. The latter possibly reflects a “sensory echo” that aids recollection.

Sarah's Story: Using the Individualized Meaning-centered Approach to Braille Literacy Education (I-M-ABLE)

I began providing braille instruction to (a pseudonym) at a residential school for blind students when she was 11 years old and had been learning the braille alphabet and whole-word contractions for more than two years. Sara was born with retinopathy of prematurity and was totally blind; and, according to verbal comprehension and working memory testing results, she was intellectually deficient. Her ability to recognize letters was consistently minimal (see Figure 1). Furthermore, when I reviewed the assessments, I discovered that identified only eight letters with 100% accuracy across the seven assessments. displayed a general lack of interest in learning to read braille and exhibited poor braille-reading mechanics and retention. She typically scrubbed (that is, moved her fingers in a circular or vertical motion over a braille character to aid in recognition) individual braille letters and had difficulty tracking and locating new lines of braille. Therefore, I decided to restart Sarah's alphabet-recognition instruction using the Mangold curriculum, which would help with her tracking and perhaps improve her ability to recognize letters at the same time. [FIGURE 1 OMITTED] After 2-1/2 months of using a traditional method of teaching to read braille and seeing her twice a week for lessons, I measured her accuracy in identifying 12 letters at 67%. At that same time, I enrolled in a series of weekly I-M-ABLE training sessions given by Diane Wormsley at the residential school at which I worked. We were asked to select a student to use as a case study as part of this training, and since I was concerned about Sarah's continued lack of retention and reading inconsistencies, I selected her as a case study during the training. I-M-ABLE is an individualized instructional method for braille that uses meaningful, student-selected vocabulary. I knew that had interests of which I was unaware, since her hobbies were not something we had discussed during previous braille lessons. After completing an interest inventory by asking questions about her favorite books, music, and things to do during leisure time, I was able to help her create a list of meaningful words. Sarah's first selection of Key Vocabulary or student-chosen words were Chris Brown, SpongeBob, pizza, and music. When the initial list was complete, I reviewed each word with Sarah. Her immediate response was, Thank you for writing all those words! At this point, it seemed as though I had some buy-in from Sarah. I then chose to introduce the words pizza and Chris Brown first on individual braille word cards because these words were tactilely distinct. When she showed success with them, I introduced SpongeBob and music. While and I looked at these words and others on braille word cards, we discussed word cues (unique distinctions of individual words, such as the characters in the words appearing tall, clumpy, spaced apart, or at the top or bottom of the braille cell). became instantly successful at recognizing her new words. Whereas she had previously not been able to recognize letters, she now was able to learn the feel of the new words using the word cues we discussed. As she learned more words, I wanted to use them in stories, which required me to introduce her to some filler words (teacher-selected words, including high-frequency words). Sarah's first filler words were likes and eats. One of the filler words allowed her to read her first key vocabulary story Likes: Sarah likes pizza. likes music. likes Chris Brown. likes SpongeBob. likes it all. By the end of the two-month-long I-MABLE workshop that I was attending, was successfully reading eight words and was using more efficient hand movements while reading (that is, she was no longer scrubbing). In addition, I watched her become extremely motivated to learn to read braille using this new approach. …

Teaching Adults to Read Braille Using Phonological Methods: Single-Case Studies

Four women with visual impairments were taught 13 braille letters as phonemes and another 13 braille letters as graphemes and then were taught 10 braille words as onset-rime and another 10 braille words as whole words. Phoneme and onset-rime instruction resulted in faster and more accurate performance.

Color Concepts and Their Organization in the Case of Blind Children

The relation between color cognition and color terms is a popular issue in the domain of language cognition. Until now, three theories have emerged: (1) the general evaluation theory of color terms, which asserts that color terms and color cognition are independent; (2) the hypothesis of linguistic reality, which declares that color terms affect color cognition; and (3) a compromised view, which integrates the previous two views. Almost all earlier studies have been conducted on sighted subjects. The dearth of studies on blind people could possibly be explained by people's belief that the blind cannot see colors. Using the methods of testing of color concepts and classification of color words, this study investigated the understanding and organization of the color words of blind children. The materials were 11 basic Chinese color terms: black, white, red, orange, yellow, green, blue, purple, palm, grey, and pink. The color terms were printed on cards, using Braille. The subjects were 85 blind children, out of which 63 were born blind and 22 were turned blind after birth. Further, 55 of the subjects were primary school pupils, and 30 were middle school pupils. The experiment involved two stages: In the first stage, the subjects were asked to name colors by touching the cards on which the Braille color words were printed and to provide some examples with regard to that color from their daily life; in the second stage, they were asked to sort the color cards into groups according to their own standards. The results were as follows. First, the order of the color concepts that the blind children got through in the test were similar to the order of the color naming by the sighted children; however there also existed differences. Second, in the semantic spaces of the color words, both the blind and sighted children manifested "colorness/colorlessness" dimensions; while the sighted children manifested the "cold color/warm color" dimension, the blind children manifested the "things' color/setting color" dimension. Third, the organization of the blind children's color concepts was characterized by thematic associations and slot-filler associations, these kinds of relations being based on the individuals' knowledge and experience, thereby emphasizing the functions of things, contexts, and the relations of events. The findings of the study were as follows: (1) there were similarities as well as differences between the order of the color concepts that the blind children got through in the test and the order of the color naming by the sighted children, and (2) the blind children manifested the "colorness/colorlessness" and "things' color/setting color" dimensions in their semantic space of color words, and the organization of the color concepts of blind children was characterized by thematic associations and slot-filler associations.