• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.30-39
• /
• 2003

In this paper, we carried out the performance evaluation of HM-Net(Hidden Markov Network) speech recognition system for Korean speech databases. We adopted to construct acoustic models using the HM-Nets modified by HMMs(Hidden Markov Models), which are widely used as the statistical modeling methods. HM-Nets are carried out the state splitting for contextual and temporal domain by PDT-SSS(Phonetic Decision Tree-based Successive State Splitting) algorithm, which is modified the original SSS algorithm. Especially it adopted the phonetic decision tree to effectively express the context information not appear in training speech data on contextual domain state splitting. In case of temporal domain state splitting, to effectively represent information of each phoneme maintenance in the state splitting is carried out, and then the optimal model network of triphone types are constructed by in the parameter. Speech recognition was performed using the one-pass Viterbi beam search algorithm with phone-pair/word-pair grammar for phoneme/word recognition, respectively and using the multi-pass search algorithm with n-gram language models for sentence recognition. The tree-structured lexicon was used in order to decrease the number of nodes by sharing the same prefixes among words. In this paper, the performance evaluation of HM-Net speech recognition system is carried out for various recognition conditions. Through the experiments, we verified that it has very superior recognition performance compared with the previous introduced recognition system.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.3
• /
• pp.149-162
• /
• 2020

This paper applied components of experience-based communication in terms of experience theory of Burnd H. Schmitt and context-based communication in the messenger platform environment through the scenario-based survey method, in order to study the influence of individual experiences, shared experiences, ubiquitous connectivity, and contextual usefulness on the perceived value and use intention of chatbot. Through this, the study is to provide companies in various service industries with practical approaches to further promote the use of chatbot. The implications of this study are as follows. First, as most chatbots still do not exceed the human planning level of designing them, it is necessary to consider how to design individual experience elements functionally according to the customer's intention to speak when developing the chatbot. Second, the chatbot should be designed not only from the perspective of completing specific tasks at any real time in anywhere, but also from the overall perspective of enhancing the quality of interaction, including the situation to which the customer belongs. Third, since the chatbot is likely to be anthropomorphized by users, it is important to be cautious about determining the chatbot's 'persona' and 'tone and manner' when developing the chatbot. Customer satisfaction is the most important criterion for the success of chatbot development. In other words, the quality of planning and data rather than the quality of artificial intelligence algorithms determines the utilization of chatbot. This is why companies are trying to make interactions with chatbot as close as possible to human interactions.

• Korean Journal of Cognitive Science
• /
• v.19 no.1
• /
• pp.89-105
• /
• 2008

In this paper, we suggest a rule-based system for the prediction of natural prosodic phrase breaks from Korean texts. For the implementation of the rule-based system, (1) sentence constituents are sub-categorized according to their syntactic functions, (2) syntactic phrases are recognized using the dependency relations among sub-categorized constituents, (3) rules for predicting prosodic phrase breaks are created. In addition, (4) the length of syntactic phrases and sentences, the position of syntactic phrases in a sentence, sense information of contextual words have been considered as to determine the variable prosodic phrase breaks. Based on these rules and features, we obtained the accuracy over 90% in predicting the position of major break and no break which have high correlation with the syntactic structure of the sentence. As for the overall accuracy in predicting the whole prosodic phrase breaks, the suggested system shows Break_Correct of 87.18% and Juncture Correct of 89.27% which is higher than that of other models.

• The KIPS Transactions:PartB
• /
• v.14B no.7
• /
• pp.559-566
• /
• 2007

Subjective sentences express opinions, emotions, evaluations and other subjective ideas relevant to products or events. These expressions sometimes can be seen in only part of a sentence, thus extracting features from a full-sentence can degrade the performance of subjective-sentence-classification. This paper presents a method for improving the performance of a subjectivity classifier by combining two classifiers generated from the different representations of an input sentence. One representation is a sentimental phrase that represents an automatically identified subjective expression or objective expression and the other representation is a full-sentence. Each representation is used to extract modified n-grams that are composed of a word and its contextual words' polarity information. The best performance, 79.7% accuracy, 2.5% improvement, was obtained when the phrase-level classifier and the sentence-level classifier were merged.

• Korean Journal of Human Ecology
• /
• v.5 no.2
• /
• pp.1-16
• /
• 1996

This study has examined multiple influences of several variables on parenting behavior by looking into illustrative studies. This study provides support to the view that various factors influence parenting and that parenting behavior is multiply determined. Characteristics of parents, children and the context in which parent-child relations occur cause different childrearing patterns among parents. This study can be summarized as follows: 1) Parental behavior is influenced to a large degree by what the parent brings to the situation. In other words, characteristics of the parent including personality characteristics, interpersonal skills, problem-solving skills, level of maturity, values and childrearing beliefs contribute to individual differences in parenting. 2) The parent's relationship history influences the personality characteristics that the parent brings to his or her adult roles. To understand who the parent is today, we have to look at who the parent was, and what the parent was doing in the years prior to parenthood. That is, we need to see the life course of the individual before parenthood. 3) Contextual variables including the immediate context and the larger context have proved to influence parental behaviors. Characteristics of the immediate context such as the quality of marital rationship can influence the parent's psychological well-being and his or her behavior toward the childen while characteristics of the larger context such as the economic situation and the neighborhood can influence the level of stress experienced by the parent and cosequently how the parent relates to his or her child. 4) In order to understand the development of the parent-child relationship we need to look at the characteristics of the child. Children may elicit positive behaviors from their parents, or they may possess characteristics that the parents find aversive thus leading to difficulties in the relationship. Therefore, much depends on the fit beween the characteristics of the parents and characteristics of the child. By examining multiple contemporaneous influences on parenting, this study could deepen the understanding of why parents have different childrearing patterns, why some parents fail to meet their children's demands and why parents act in certain ways. What we ultimately hope is that as we learn more about parenting and the development of parent-child relationships, we will be better able to provide parents with the supports they need to achieve their parenting goals.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.9
• /
• pp.1702-1709
• /
• 1994

In the postprocessing of Hangul recognition system, the storage structure of contextual information is an important matter for the recognition rate and speed of the entire system. Trie in general is used to represent the context as word dictionary, but the memory space efficiency of the structure is low. Therefore we propose a new structure for word dictionary that has better space efficiency and the equivalent merits of trie. Because Hangul is a compound language, the language can be represented by phonemes or by characters. In the representation by phonemes(P-mode) the retrieval is fast, but the space efficiency is low. In the representation by characters(C-mode) the space efficiency is high, but the retrieval is slow. In this paper the two representation methods are combined to form a hybrid representation(H-mode). At first an optimal level for the combination is selected by two characteristic curves of node utilization and dispersion. Then the input words are represented with trie structure by P-mode from the first to the optimal level, and the rest are represented with sequentially linked list structure by C-mode. The experimental results for the six kinds of word set show that the proposed structure is more efficient. This result is based on the fact that the retrieval for H-mode is as fast as P-mode and the space efficiency is as good as C-mode.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.55-61
• /
• 2019

In order to realize foreign language education, various existing educational media have been provided, but there are disadvantages in that the cost of the parish and the media program is high and the real-time responsiveness is poor. In this paper, we propose an artificial intelligence English conversation system based on VR and speech recognition. We used Google CardBoard VR and Google Speech API to build the system and developed artificial intelligence algorithms for providing virtual reality environment and talking. In the proposed speech recognition server system, the sentences spoken by the user can be divided into word units and compared with the data words stored in the database to provide the highest probability. Users can communicate with and respond to people in virtual reality. The function provided by the conversation is independent of the contextual conversations and themes, and the conversations with the AI assistant are implemented in real time so that the user system can be checked in real time. It is expected to contribute to the expansion of virtual education contents service related to the Fourth Industrial Revolution through the system combining the virtual reality and the voice recognition function proposed in this paper.

• Perspectives in Nursing Science
• /
• v.16 no.1
• /
• pp.45-54
• /
• 2019

Purpose: The purposes of this study was to review the literature on intervention for treating anxiety and depression among unmarried mothers living in facilities, and to understand core that could promote the development of more effective interventions. Methods: Key words in English and Korean were used to search through eight electronic databases-PubMed, Cochrane Library, EMBASE, CINAHL, RISS, DBpia, NDSL, and the National Assembly Library. Results: Ten studies were ultimately selected for the integrative review and were evaluated in terms of contextual and methodological quality. The studies consisted of seven quasi-experimental studies and three case report studies. The selected studies utilized music, art, forest therapy, dancing, education, and play programs to change mothers' perceptions, emotions, and behavior and to improve their relationships with their babies or others. Conclusion: It is important to consider mothers' self-awareness and emotional expression, and to improve their relationships with their babies or others as core elements when developing intervention programs for anxiety and/or depression among unmarried mothers living in residential facilities.

• Journal of Korean Society of Archives and Records Management
• /
• v.19 no.4
• /
• pp.211-219
• /
• 2019

To research the directionality of Korean literary archives, this paper introduces the modern literature archive of the National Library of Korea and discusses the future direction of the archive of the National Museum of Korean Literature. The modern literature archive of the National Library of Korea is operated with focus on digitizing the original text of modern literature, providing professional release information, and constructing contents related to modern writers and literary history. As such, the National Museum of Korean Literature, which aims to open in 2023, needs to refer to the case of the National Library of Korea but introduce more professional curating. In other words, the archivist should have the initiative to document the context of the records so that literature can be reproduced creatively based on the archived data. Moreover, he/she should actively implement archive policies to expand the availability of materials.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.332-340
• /
• 2022

Recently, with the development of deep learning and artificial neural network technologies, research on the application of neural network has been actively conducted in the field of video coding. In particular, deep learning-based intra prediction is being studied as a way to overcome the performance limitations of the existing intra prediction techniques. This paper presents a method of context-adaptive neural network-based intra prediction model training and its coding performance analysis. In other words, in this paper, we implement and train a known intra prediction model based on convolutional neural network (CNN) that predicts a current block using contextual information from reference blocks. Then, we integrate the trained model into HM16.19 as an additional intra prediction mode and evaluate the coding performance of the trained model. Experimental results show that the trained model gives 0.28% BD-rate bit saving over HEVC in All Intra (AI) coding mode. In addition, the coding performance change of training considering block partition is also presented.