• Journal of the Korea Society of Computer and Information
• /
• v.14 no.8
• /
• pp.65-71
• /
• 2009

Natural language processing is necessary in order to efficiently perform filtering tremendous information produced in information retrieval of world wide web. This paper suggested an algorithm for meaning of numerals in the text. The algorithm for meaning of numerals utilized context-free grammars with the chart parsing technique, interpreted affixes connected with the numerals and was designed to disambiguate their meanings systematically supported by the n-gram based words. And the algorithm was designed to use POS (part-of-speech) taggers, to automatically recognize restriction conditions of trigram words, and to gradually disambiguate the meaning of the numerals. This research performed experiment for the suggested system of the numeral interpretation. The result showed that the frequency-proportional method recognized the numerals with 86.3% accuracy and the condition-proportional method with 82.8% accuracy.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.13-26
• /
• 2024

Multi-modal generation is the process of generating results based on a variety of information, such as text, images, and audio. With the rapid development of AI technology, there is a growing number of multi-modal based systems that synthesize different types of data to produce results. In this paper, we present an AI system that uses speech and text recognition to describe a person and generate a montage image. While the existing montage generation technology is based on the appearance of Westerners, the montage generation system developed in this paper learns a model based on Korean facial features. Therefore, it is possible to create more accurate and effective Korean montage images based on multi-modal voice and text specific to Korean. Since the developed montage generation app can be utilized as a draft montage, it can dramatically reduce the manual labor of existing montage production personnel. For this purpose, we utilized persona-based virtual person montage data provided by the AI-Hub of the National Information Society Agency. AI-Hub is an AI integration platform aimed at providing a one-stop service by building artificial intelligence learning data necessary for the development of AI technology and services. The image generation system was implemented using VQGAN, a deep learning model used to generate high-resolution images, and the KoDALLE model, a Korean-based image generation model. It can be confirmed that the learned AI model creates a montage image of a face that is very similar to what was described using voice and text. To verify the practicality of the developed montage generation app, 10 testers used it and more than 70% responded that they were satisfied. The montage generator can be used in various fields, such as criminal detection, to describe and image facial features.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.45-48
• /
• 2008

Using these systems, additional information on the paintings and exhibits may be provided in the forms of text, image, speech, and video However, at museums and exhibitions, many tourists are often interested in exhibits of some particular style, authors, or coteries. The proposed Augmented Reality based guidance system may guide the users to exhibits of their interest for selective viewing. Location of the next exhibit of interest may be informed to the users as well as additional multimedia information on the exhibits of interest Such information is shown on the Augmented Reality views of the user's display device. The proposed system is composed an Ultra-Mobile PC (UMPC), an inertia tracker, and a camera. In the beginning, the user may select his/her preference on the exhibits from the menu, and then the system starts guiding by showing the relative orientation, distance, and visual cue to find a next exhibit. When the user finds and locates the matching visual cue within a matching box of the display screen, the system provides multimedia information on the exhibit. According to the preliminary user test, the proposed system is convenient and useful for navigating through large-scale exhibition.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.2
• /
• pp.87-93
• /
• 2018

This Study Propose A New Approach To Impliment A Intelligent Robot Control Based on Voice Recognition For Smart Factory Automation Since human usually communicate each other by voices, it is very convenient if voice is used to command humanoid robots or the other type robot system. A lot of researches has been performed about voice recognition systems for this purpose. Hidden Markov Model is a robust statistical methodology for efficient voice recognition in noise environments. It has being tested in a wide range of applications. A prediction approach traditionally applied for the text compression and coding, Prediction by Partial Matching which is a finite-context statistical modeling technique and can predict the next characters based on the context, has shown a great potential in developing novel solutions to several language modeling problems in speech recognition. It was illustrated the reliability of voice recognition by experiments for humanoid robot with 26 joints as the purpose of application to the manufacturing process.

• Journal of the Korea Convergence Society
• /
• v.9 no.10
• /
• pp.199-208
• /
• 2018

In this paper, Hwang Soon-won's "Sonagi" is considered from the aspect of literary imagination reconstructed into a fusion content of various cultures such as HD TV Literature, Animation, Movie, Musical, CF and the part which changed from the original text. In the TV literature Museum "Sonagi" he created a newly person called a 'Seok-yi' who is a young brother of a boy, a girl's mother who did not exist in the original, and developed the composition more precisely. And In the animation, the main character's dialogue is presented as a speech and it is characteristic that the theme of the work is revealed more effectively. On the other hand, the heroine in the movie says, "I do not like the ending part of the showers." Also In the musical "Sonagi", about 2 tons of water was used to give more vividness and presence to the audience. In this way, the contents of the original works are transformed according to the characteristics of the medium in the various cultural fusion contents based on novels, and thus convey the unique imagination of the director to the audience.

• The KIPS Transactions:PartC
• /
• v.12C no.7 s.103
• /
• pp.1067-1074
• /
• 2005

The mobile user interface becomes important to access information fast and conveniently, especially in the ubiquitous computing environment. Among many new services in the mobile computing environment, ubiquitous information networking service was studied using korean alphabet (consonant or vowel) domain-names including Korean single-character domain-names. Instead of handling long English/Korean URL-strings, as convenient user interface for information access, the Korean single-character/alphabet domain names are more convenient than long URL strings to retrieve information and to send information in the wired Internet as well as in the mobile Internet. We studied the convenience of Korean alphabet domain names with PCs as well as with mobile phones. We introduce the Implementation and the application of ubiquitous information portal, which has the functionality of Text to Speech (TTS) and is accessible with Korean single - character/alphabet domain - names.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1329-1338
• /
• 2021

There are rarely effective methods to help visually impaired people when they want to know the expiration date of products excepted to only Braille. In this study, we developed an expiration date notification system based on YOLO and OCR for visually impaired people. The handicapped people can automatically know the expiration date of a specific product by using our system without the help of a caregiver, fast and accurately. The proposed system is worked by four different steps: (1) identification of a target product by scanning its barcode; (2) segmentation of an image area with the expiration date using YOLO; (3) classification of the expiration date by OCR: (4) notification of the expiration date by TTS. Our system showed an average classification accuracy of about 86.00% when blindfolded subjects used the proposed system in real-time. This result validates that the proposed system can be potentially used for visually impaired people.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.23-29
• /
• 2022

Virtual humans are implemented with dedicated modeling tools like Unity 3D Engine in virtual space (virtual reality, mixed reality, metaverse, etc.). Various human modeling tools have been introduced to implement virtual human-like appearance, voice, expression, and behavior similar to real people, and virtual humans implemented via these tools can communicate with users to some extent. However, most of the virtual humans so far have stayed unimodal using only text or speech. As AI technologies advance, the outdated machine-centered dialogue system is now changing to a human-centered, natural multi-modal system. By using several pre-trained networks, we implemented an emotion-based multi-modal dialogue system, which generates human-like utterances and displays appropriate facial expressions in real-time.

• Journal of KIISE
• /
• v.44 no.3
• /
• pp.306-313
• /
• 2017

Named entity recognition (NER) seeks to locate and classify named entities in text into pre-defined categories such as names of persons, organizations, locations, expressions of times, etc. Recently, many state-of-the-art NER systems have been implemented with bidirectional LSTM CRFs. Deep learning models based on long short-term memory (LSTM) generally depend on word representations as input. In this paper, we propose an approach to expand word representation by using pre-trained word embedding, part of speech (POS) tag embedding, syllable embedding and named entity dictionary feature vectors. Our experiments show that the proposed approach creates useful word representations as an input of bidirectional LSTM CRFs. Our final presentation shows its efficacy to be 8.05%p higher than baseline NERs with only the pre-trained word embedding vector.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.190-194
• /
• 2008

This paper presents a speaker identification technique which is one of the basic techniques of the ubiquitous robot companion. Though the conventional mel-frequency cepstral coefficients guarantee high performance of speaker identification in clean condition, the performance is degraded dramatically in noise condition. To overcome this problem, we employed the relative autocorrelation sequence mel-frequency cepstral coefficient which is one of the noise robust features. However, there are two problems in relative autocorrelation sequence mel-frequency cepstral coefficient: 1) the limited information problem. 2) the residual noise problem. In this paper, to deal with these drawbacks, we propose a multi-streaming method for the limited information problem and a hybrid method for the residual noise problem. To evaluate proposed methods, noisy speech is used in which air conditioner noise, classic music, and vacuum noise are artificially added. Through experiments, proposed methods provide better performance of speaker identification than the conventional methods.