• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• Phonetics and Speech Sciences
• /
• v.12 no.3
• /
• pp.95-103
• /
• 2020

The current study aimed to identify the characteristics of speech rate and pause in children with spastic cerebral palsy (CP) and their relationships with speech intelligibility. In all, 26 children with CP, 4 with no speech motor involvement and age-appropriate language ability (NSMI-LCT), 6 with no speech motor involvement and impaired language ability (NSMI-LCI), 6 with speech motor involvement and age-appropriate language ability (SMI- LCT), and 10 with speech motor involvement and impaired language ability (SMI-LCI) participated in the study. Speech samples for the speech rate and pause analysis were extracted using a sentence repetition task. Acoustic analysis were made in Praat. First, it was found that regardless of the presence of language impairment, significant group differences between the NSMI and SMI groups were found in speech rate and articulation rate. Second, the SMI groups showed a higher ratio of pause time to sentence production time, more frequent pauses, and longer durations of pauses than the NSMI groups. Lastly, there were significant correlations among speech rate, articulation rate, and intelligibility. These findings suggest that slow speech rate is the main feature in SMI groups, and that both speech rate and articulation rate play important roles in the intelligibility of children with spastic CP.

• Journal of Music and Human Behavior
• /
• v.21 no.1
• /
• pp.49-68
• /
• 2024

This study aims to acoustically analyze Korean language characteristics and convert these findings into musical elements, providing foundational data for evidence-based music-language rehabilitation. We collected voice data from thirty men and thirty women aged 19-25, each providing six-syllable prosodic units composed of two accentual phrases, including both declarative and interrogative sentences. Analyzing this data with Praat, we extracted syllabic acoustic properties and conducted statistical analyses based on acoustic properties, sentence type, gender, and particle presence. Significant differences were found in syllable frequency and duration based on accentual phrases and prosodic units (p < .001), with interrogative showing higher frequencies and declaratives longer durations (p < .001). Female frequencies were significantly higher than males' (p < .001), with longer durations observed (p < .001). Particle syllables also showed significantly stronger intensities (p < .001). Finally, we presented melodies converted from these acoustic properties into musical scores based on pitch, duration, and accent. The insights from this analysis of six-syllable Korean sentences will guide further research on developing a system for melodizing large-scale Korean speech data, expected to be crucial in music-based language rehabilitation.

• Journal of the Korean Home Economics Association
• /
• v.47 no.10
• /
• pp.87-95
• /
• 2009

This study conducted a content analysis of the treatises published in JKHEA(Journal of the Korean Home Economics Association). In total, 2,136 articles published in JKHEA from 1995 to the first half of 2009 were reviewed. Articles were classified by subject matters, research methods, number of researchers, presence of research fund, language and number of reference. Although it is useful to employ content analysis in reviewing academic articles on human ecology in all journal publications, the sheer size of literature available makes this task nearly impossible. As such, we have chosen JKHEA as a popular representative journal on human ecology. This study presented the empirical results of research trends and other characteristics in JKHEA. As such, the results of this study presented a snapshot analysis of research on human ecology and future trends.

• English Language & Literature Teaching
• /
• v.11 no.2
• /
• pp.111-134
• /
• 2005

This paper examines high school English textbooks to ascertain if they appropriately reflect the kinds and frequencies of routine formulas and downgraders of request act used by English native speakers. It is important to present authentic routine formulas in textbooks for students to acquire proper, efficient and safe communication strategies to communicate with other English speakers. For the analysis, currently available 7 series of 21 high school English textbooks under the $7^{th}$ National Curriculum were selected. Each series of textbooks contains 3 school grade textbooks as High School English, High School English I, and High School English II. The results show that the high school English textbooks generally demonstrate a secund reflection of the English native speakers' use of request strategies and downgraders. That is, the textbooks were found to have presented mostly casual forms of routine formulas while they have not presented sufficient coverage of elaborated polite routine formulas for requesting which English native speakers frequently use. The presence of some kinds of the frequently used downgraders was also very small in proportion in the textbooks. More effort should be given to complement the deficiency in this area by teachers and researchers.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.22 no.1
• /
• pp.3-9
• /
• 2011

Autism and autistic spectrum disorder are chronic neuro-developmental disorders characterized by social and language impairments and stereotyped, repetitive patterns of behavior. The etiology of autism remains unknown; however, a strong genetic component has been detected and environmental factors may also be involved in their etiologies. In the current study, we reviewed evidence for the presence of prenatal and perinatal factors, gastrointestinal factors, food allergies, metabolic and heavy metal factors, and other nutritional factors that may represent risk factors for the development of autism and autistic spectrum disorder.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.271-275
• /
• 2005

In this research, we propose a Unified Fuzzy rule-based knowledge Inference Systems UFIS) to help the expert in cosmetic brand detection. Users' preferred cosmetic product detection is very important in the level of CRM. To this Purpose, many corporations trying to develop an efficient data mining tool. In this study, we develop a prototype fuzzy rule detection and inference system. The framework used in this development is mainly based on two different mechanisms such as fuzzy rule extraction and RDB (Relational DB)-based fuzzy rule inference. First, fuzzy clustering and fuzzy rule extraction deal with the presence of the knowledge in data base and its value is presented with a value between $0\∼1$. Second, RDB and SQL(Structured Query Language)-based fuzzy rule inference mechanism provide more flexibility in knowledge management than conventional non-fuzzy value-based KMS(Knowledge Management Systems)

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.4
• /
• pp.353-359
• /
• 2005

In this research, we propose a Unified Fuzzy rule-based knowledge Inference Systems (UFIS) to help the expert in cosmetic brand detection. Users' preferred cosmetic product detection is very important in the level of CRM. To this purpose, many corporations trying to develop an efficient data mining tool. In this study, we develop a prototype fuzzy rule detection and inference system. The framework used in this development is mainly based on two different mechanisms such as fuzzy rule extraction and RDB (Relational DB)-based fuzzy rule inference. First, fuzzy clustering and fuzzy rule extraction deal with the presence of the knowledge in data base and its value is presented with a value between 0 -1. Second, RDB and SQL (Structured Query Language)-based fuzzy rule inference mechanism provide more flexibility in knowledge management than conventional non-fuzzy value-based KMS (Knowledge Management Systems).

• Korean Journal of Cognitive Science
• /
• v.31 no.4
• /
• pp.155-178
• /
• 2020

People read in different settings, including when music is playing in the background. Whether the presence of music facilitates, hinders, or does not affect language processing is an on-going debate in the current literature. The present study used ERPs to examine the influence of music on orthographic, semantic, and syntactic processing by inspecting P2, N400, and P600 responses, respectively. A total of 60 participants judged the correctness of visually presented sentences while listening to music with lyrics, music without lyrics, or in silence. The results showed that the P2 and P600 effects were larger in the silent condition than in the music-with-lyrics condition, while there were no N400 differences among the conditions. This indicates that only lyrical music interferes with orthographic and syntactic language processing, while it has no, or minimal, effect on semantic processing. The results are discussed in relation to the background music interference effect.

• Knowledge Management Research
• /
• v.25 no.1
• /
• pp.155-172
• /
• 2024

This study investigates the effectiveness of foreign language learning through diverse treatments in virtual settings, particularly by differentiating virtual environments with three textual enhancement techniques. A 2 × 3 mixed-factorial design was used, treating virtual environments as within-subject factors and textual enhancement techniques as between-subject factors. Participants experienced two videos, each in different virtual learning environments with one of the random textual enhancement techniques. The results showed that the interaction between different virtual environments and textual enhancement techniques had a statistically significant impact on presence among groups. In examining main effects of virtual environments, significant differences were observed in flow and attitude toward pre-post learning. Also, main effects of textual enhancements notably influenced flow, intention to use, learning satisfaction, and learning confidence. This study highlights the potential of Metaverse in foreign language learning, suggesting that learner experiences and effects vary with different virtual environments.