• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.3
• /
• pp.177-183
• /
• 2020

Steganography uses digital images as a medium for sending secret messages over insecure networks. There is also a least significant bit(LSB) that is a popular method of embedding secret messages in digital images. The goal of steganography is to securely and flawlessly transmit secret messages using stego media over a communication channel. There is a need for a method to improve resistance to reduce the risk of exposure to third parties. To safely hide secret messages, I propose new algorithms that go through crossing, encryption, chaos and concealment steps. After separating Hangul syllables into choseong, jungseong and jongseong, the bitwised message information is encrypted. After applying the logistic map, bitwised information is reconstructed using the position of the chaotic sequence. The secret message is inserted into the randomly selected RGB channel. PSNR and SSIM were used to confirm the effectiveness of the applied results. It was confirmed as 44.392(dB) and 0.9884, respectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.8
• /
• pp.1625-1631
• /
• 2005

This paper describes an optimization of a language model and an acoustic model that improve the ability of speech recognition with Korean nit digit. Recognition errors of the language model are decreasing by analysis of the grammatical feature of korean unit digits, and then is made up of fsn-node with a disyllable. Acoustic model make use of demi-syllable pair to decrease recognition errors by inaccuracy division of a phone, a syllable because of a monosyllable, a short pronunciation and an articulation. we have used the k-means clustering algorithm with the transformed successive state splining in feature level for the efficient modelling of the feature of recognition unit . As a result of experimentations, $10.5\%$ recognition rate is raised in the case of the proposed language model. The demi-syllable pair with an acoustic model increased $12.5\%$ recognition rate and $1.5\%$ recognition rate is improved in transformed successive state splitting.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.54-61
• /
• 2016

Because a word is the basic unit of language processing, studies of the word recognition processing and the variables that contribute to word recognition processing are very important. Word frequency and word length are recognized as important factors on word recognition. This study examined the effects of those two variables on the Korean word recognition processing. In Experiment 1, two types of Hangul words, pure Hangul words and Hangul words with Hanja counterparts, were used to explore the frequency effects. A frequency effect was not observed for Hangul words with Hanja counterparts. In Experiment 2, the word length was manipulated to determine if the word length effect appears in Hangul words. Contrary to the expectation, one syllable words were processed more slowly than two syllable words. The possible explanations for these results and future research directions are discussed.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.11
• /
• pp.41-49
• /
• 2019

We are to build an unsupervised machine learning-based language model which can estimate the amount of information that are in need to process words consisting of subword-level morphemes and syllables. We are then to investigate whether the reading times of words reflecting their morphemic and syllabic structures are predicted by an information-theoretic measure such as surprisal. Specifically, the proposed Morfessor-based unsupervised machine learning model is first to be trained on the large dataset of sentences on Sejong Corpus and is then to be applied to estimate the information-theoretic measure on each word in the test data of Korean words. The reading times of the words in the test data are to be recruited from Korean Lexicon Project (KLP) Database. A comparison between the information-theoretic measures of the words in point and the corresponding reading times by using a linear mixed effect model reveals a reliable correlation between surprisal and reading time. We conclude that surprisal is positively related to the processing effort (i.e. reading time), confirming the surprisal hypothesis.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.10
• /
• pp.1-7
• /
• 2021

Recently, since most of the research on correcting speech recognition errors is based on English, there is not enough research on Korean speech recognition. Compared to English speech recognition, however, Korean speech recognition has many errors due to the linguistic characteristics of Korean language, such as Korean Fortis and Korean Liaison, thus research on Korean speech recognition is needed. Furthermore, earlier works primarily focused on editorial distance algorithms and syllable restoration rules, making it difficult to correct the error types of Korean Fortis and Korean Liaison. In this paper, we propose a context-sensitive post-processing model of speech recognition using a LSTM-based sequence-to-sequence model and Bahdanau attention mechanism to correct Korean speech recognition errors caused by the pronunciation. Experiments showed that by using the model, the speech recognition performance was improved from 64% to 77% for Fortis, 74% to 90% for Liaison, and from 69% to 84% for average recognition than before. Based on the results, it seems possible to apply the proposed model to real-world applications based on speech recognition.

• Science of Emotion and Sensibility
• /
• v.24 no.1
• /
• pp.3-10
• /
• 2021

This study examined the effect of intentional thought avoidance(i.e., thought suppression and thought substitution) using "Think and No Think" task. Two syllable words were selected, and recall test was performed with a single subject group. recall accuracy of them was measured in two recall conditions(cue recall and target recall) and four training conditions(thought, thought suppression, thought substitution, and baseline). The results showed that recall accuracy in cue recall condition was better than in target recall condition, regardless of training conditions, and recall accuracy in thought condition was better than in other training conditions, regardless of recall conditions. Also there was significant interaction between recall and training conditions: For thought suppression. there was no difference between two recall conditions, whereas for thought substitution, recall accuracy in cue recall condition was better than in target condition. These findings indicate that thought avoidance strategies, including both thought suppression and thought substitution, are effective in avoiding the specific thought intentionally, and thought suppression and thought substitution could be applied by different mechanism.

• Journal of Advanced Navigation Technology
• /
• v.15 no.2
• /
• pp.287-297
• /
• 2011

As electronic mails are being widely used for facility and speedness of information communication, as the amount of spam mails which have malice and advertisement increase and cause lots of social and economic problem. A number of approaches have been proposed to alleviate the impact of spam. These approaches can be categorized into pre-acceptance and post-acceptance methods. Post-acceptance methods include bayesian filters, collaborative filtering and e-mail prioritization which are based on words or sentances. But, spammers are changing those characteristics and sending to avoid filtering system. In the case of Korean, the abnormal usages can be much more than other languages because syllable is composed of chosung, jungsung, and jongsung. Existing formal expressions and learning algorithms have the limits to meet with those changes promptly and efficiently. So, we present an methods for recognizing Korean abnormal language(Koral) to improve accuracy and efficiency of filtering system. The method is based on syllabic than word and Smith-waterman algorithm. Through the experiment on filter keyword and e-mail extracted from mail server, we confirmed that Koral is recognized exactly according to similarity level. The required time and space costs are within the permitted limit.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.99-120
• /
• 2017

In order to develop a semiautomatic support system that allows researchers concerned to efficiently analyze the technical trends for the ever-growing industry and market. This paper introduces a couple of Korean sentence generation models that can automatically generate definitional statements as well as descriptions of technical terms and concepts. The proposed models are based on a deep learning model called LSTM (Long Sort-Term Memory) capable of effectively labeling textual sequences by taking into account the contextual relations of each item in the sequences. Our models take technical terms as inputs and can generate a broad range of heterogeneous textual descriptions that explain the concept of the terms. In the experiments using large-scale training collections, we confirmed that more accurate and reasonable sentences can be generated by CHAR-CNN-LSTM model that is a word-based LSTM exploiting character embeddings based on convolutional neural networks (CNN). The results of this study can be a force for developing an extension model that can generate a set of sentences covering the same subjects, and furthermore, we can implement an artificial intelligence model that automatically creates technical literature.

• Phonetics and Speech Sciences
• /
• v.16 no.3
• /
• pp.79-86
• /
• 2024

Transformer models have shown remarkable performance in extracting meaningful information from sequential input data such as text and images, and are gaining attention as end-to-end models for speech recognition. This study compared the performances of the Transformer speech recognition model and its enhanced versions, the Conformer and E-Branchformer, when applied to Korean speech recognition. Using Korean speech data from AIHub, we prepared a training set of approximately 7,500 hours and evaluated the models using the ESPnet toolkit. Additionally, we compared syllables and subwords as recognition units and analyzed the performance differences with changes in the number of tokens using Byte Pair Encoding. The results showed that the E-Branchformer achieved the best performance in Korean speech recognition and Conformer outperformed Transformer but degraded in performance for long utterances owing to cross-attention alignment errors. We aimed to determine the optimal settings by analyzing the performance changes with subword token adjustments. This study comprehensively evaluated model accuracy and processing speed to maximize the efficiency of Korean speech recognition. This is expected to contribute to the training of large-scale Korean speech recognition models and improve Conformer recognition errors. Future research should include additional experiments with diverse Korean speech datasets and enhance the recognition performance through structural improvements in the Conformer.

• Sijohaknonchong
• /
• v.23
• /
• pp.33-48
• /
• 2005

In my paper, the discussion focuses on the fact that sijo is distinguished from free verse as a separate Identity in that it has its own formal beauty, and the works that deviate from this poetic rule are guarded against. In the past ancient sijo, in terms of both music and literature, was a major genre in harmony with chang(songs) ; and in modern times, sijo been created irrelevantly with chug. But my point is that it will not futile if sijo is accompanied with chang, and, therefore, the latter should be adjusted to a modern taste and go together with the former ; and that, to attain this goal, Korean musicans should cooperate with sijo writers. With English-version sijo works, there are some that are put in accordance with the formality of Engish poetry. This paper indicates that, in this case, foreign readers can't feel the nuances the source text of sijo works could produce, so it is not proper to translate sijo works in accordance with the formality of English poetry. But there are other translations where the 3-jang(statements)-6-gu(phrases) form of the original sijo text is reproduced within the limits of English expressions, with each of the two gu(phrases) in a ing(statement) having an almost equal number of syllables, so that each phrase could be recited within the same length of time. The conclusion is that the Korean-English translations of sijo works should begin with the reproduction of its original formal beauty; but, to do this, sijo writers should create works in accordance with it original formality first. Therefore for good translations of sijo works there should be a mutual efforts between sijo scholars and English poetry scholars.