• The Journal of the Acoustical Society of Korea
• /
• v.20 no.6
• /
• pp.40-45
• /
• 2001

In this paper, we implemented a multimodal system combining speech and lip information, and evaluated its performance. We designed speech recognizer using speech information and lip recognizer using image information. Both recognizers were based on HMM recognition engine. As a combining method we adopted the late integration method in which weighting ratio for speech and lip is 8:2. By the way, Our constructed multi-modal recognition system was ported on DARC system. That is, our system was used to control Comdio of DARC. The interrace between DARC and our system was done with TCP/IP socked. The experimental results of controlling Comdio showed that lip recognition can be used for an auxiliary means of speech recognizer by improving the rate of the recognition. Also, we expect that multi-model system will be successfully applied to o traffic information system and CNS (Car Navigation System).

• 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.

• Journal of the Korea Convergence Society
• /
• v.9 no.1
• /
• pp.419-431
• /
• 2018

In this paper, we propose a novel method for monitoring mood trend of Twitter users by analyzing their daily tweets for a long period. Then, to more accurately understand their tweets, we analyze all types of content in tweets, i.e., texts and emoticons, and images, thus develop a multimodal sentiment analysis method. In the proposed method, two single-modal analyses first are performed to extract the users' moods hidden in texts and images: a lexicon-based and learning-based text classifier and a learning-based image classifier. Thereafter, the extracted moods from the respective analyses are combined into a tweet mood and aggregated a daily mood. As a result, the proposed method generates a user daily mood flow graph, which allows us for monitoring the mood trend of users more intuitively. For evaluation, we perform two sets of experiment. First, we collect the data sets of 40,447 data. We evaluate our method via comparing the state-of-the-art techniques. In our experiments, we demonstrate that the proposed multimodal analysis method outperforms other baselines and our own methods using text-based tweets or images only. Furthermore, to evaluate the potential of the proposed method in monitoring users' mood trend, we tested the proposed method with 40 depressive users and 40 normal users. It proves that the proposed method can be effectively used in finding depressed users.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.67-77
• /
• 2004

The recent research has been focused on fusion of audio and visual features for reliable speech recognition in noisy environments. In this paper, we propose a neural network based model of robust speech recognition by integrating audio, visual, and contextual information. Bimodal Neural Network(BMNN) is a multi-layer perception of 4 layers, each of which performs a certain level of abstraction of input features. In BMNN the third layer combines audio md visual features of speech to compensate loss of audio information caused by noise. In order to improve the accuracy of speech recognition in noisy environments, we also propose a post-processing based on contextual information which are sequential patterns of words spoken by a user. Our experimental results show that our model outperforms any single mode models. Particularly, when we use the contextual information, we can obtain over 90% recognition accuracy even in noisy environments, which is a significant improvement compared with the state of art in speech recognition. Our research demonstrates that diverse sources of information need to be integrated to improve the accuracy of speech recognition particularly in noisy environments.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.4 s.316
• /
• pp.36-44
• /
• 2007

In this paper, we implement the speech & face recognition system to support various ubiquitous sensor network application services such as switch control, authentication, etc. using wireless audio and image interface. The proposed system is consist of the H/W with audio and image sensor and S/W such as speech recognition algorithm using psychoacoustic model, face recognition algorithm using PCA (Principal Components Analysis) and LDPC (Low Density Parity Check). The proposed speech and face recognition systems are inserted in a HOST PC to use the sensor energy effectively. And improve the accuracy of speech and face recognition, we implement a FEC (Forward Error Correction) system Also, we optimized the simulation coefficient and test environment to effectively remove the wireless channel noises and correcting wireless channel errors. As a result, when the distance that between audio sensor and the source of voice is less then 1.5m FAR and FRR are 0.126% and 7.5% respectively. The face recognition algorithm step is limited 2 times, GAR and FAR are 98.5% and 0.036%.

• Smart Structures and Systems
• /
• v.14 no.2
• /
• pp.159-189
• /
• 2014

One of the most important requirements in the evaluation of existing structural systems and ensuring a safe performance during their service life is damage assessment. Damage can be defined as a weakening of the structure that adversely affects its current or future performance which may cause undesirable displacements, stresses or vibrations to the structure. The mass and stiffness of a structure will change due to the damage, which in turn changes the measured dynamic response of the system. Damage detection can increase safety, reduce maintenance costs and increase serviceability of the structures. Artificial Neural Networks (ANNs) are simplified models of the human brain and evolved as one of the most useful mathematical concepts used in almost all branches of science and engineering. ANNs have been applied increasingly due to its powerful computational and excellent pattern recognition ability for detecting damage in structural engineering. This paper presents and reviews the technical literature for past two decades on structural damage detection using ANNs with modal parameters such as natural frequencies and mode shapes as inputs.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.141-147
• /
• 2024

Recently, there has been growing interest in personalized services tailored to an individual's preferences. This has led to ongoing research aimed at recognizing and leveraging an individual's personality traits. Among various methods for personality assessment, the OCEAN model stands out as a prominent approach. In utilizing OCEAN for personality recognition, a multi modal artificial intelligence model that incorporates linguistic, paralinguistic, and non-linguistic information is often employed. This paper examines the impact of the margin value set for extracting facial areas from video data on the accuracy of a personality recognition model that uses facial expressions to determine OCEAN traits. The study employed personality recognition models based on 2D Patch Partition, R2plus1D, 3D Patch Partition, and Video Swin Transformer technologies. It was observed that setting the facial area extraction margin to 60 resulted in the highest 1-MAE performance, scoring at 0.9118. These findings indicate the importance of selecting an optimal margin value to maximize the efficiency of personality recognition models.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.4
• /
• pp.420-430
• /
• 2003

This paper presents an immersive multimodal Gumdo simulation game that allows a user to experience the whole body interaction with an intelligent cyber fencer. The proposed system consists of three modules: (i) a nondistracting multimodal interface with 3D vision and speech (ii) an intelligent cyber fencer and (iii) an immersive feedback by a big screen and sound. First, the multimodal Interface with 3D vision and speech allows a user to move around and to shout without distracting the user. Second, an intelligent cyber fencer provides the user with intelligent interactions by perception and reaction modules that are created by the analysis of real Gumdo game. Finally, an immersive audio-visual feedback by a big screen and sound effects helps a user experience an immersive interaction. The proposed system thus provides the user with an immersive Gumdo experience with the whole body movement. The suggested system can be applied to various applications such as education, exercise, art performance, etc.

• Journal of the Ergonomics Society of Korea
• /
• v.30 no.1
• /
• pp.195-202
• /
• 2011

Objective: The aim of this study is to investigate and review the previous researches about objective measuring fatigue caused by visual stimuli. Also, we analyze possibility of alternative visual fatigue measurement methods using facial expression recognition and gesture recognition. Background: In most previous researches, visual fatigue is commonly measured by survey or interview based subjective method. However, the subjective evaluation methods can be affected by individual feeling's variation or other kinds of stimuli. To solve these problems, signal and image processing based visual fatigue measurement methods have been widely researched. Method: To analyze the signal and image processing based methods, we categorized previous works into three groups such as bio-signal, brainwave, and eye image based methods. Also, the possibility of adopting facial expression or gesture recognition to measure visual fatigue is analyzed. Results: Bio-signal and brainwave based methods have problems because they can be degraded by not only visual stimuli but also the other kinds of external stimuli caused by other sense organs. In eye image based methods, using only single feature such as blink frequency or pupil size also has problem because the single feature can be easily degraded by other kinds of emotions. Conclusion: Multi-modal measurement method is required by fusing several features which are extracted from the bio-signal and image. Also, alternative method using facial expression or gesture recognition can be considered. Application: The objective visual fatigue measurement method can be applied into the fields of quantitative and comparative measurement of visual fatigue of next generation display devices in terms of human factor.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.6
• /
• pp.603-610
• /
• 2015

This paper presents a multimodal sensor system that can determine the location of house space by analyzing the postures and heights of the residents. It consists of two sensors: a tilt sensor and an altimeter sensor. The tilt sensor measures the static and dynamic postures of the residents, and the altimeter sensor measures their heights. The sensor system includes a Bluetooth transmitter, and the server receives the measured data and determines the location in the house. We describe the process determining the locations of the residents after analyzing their postures and behaviors from the measured data. We also demonstrate the usefulness of the proposed system by applying it to a real environment.