• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.9
• /
• pp.763-770
• /
• 2004

The important issue of emotion recognition from speech is a feature extracting and pattern classification. Features should involve essential information for classifying the emotions. Feature selection is needed to decompose the components of speech and analyze the relation between features and emotions. Specially, a pitch of speech components includes much information for emotion. Accordingly, this paper searches the relation of emotion to features such as the sound loudness, pitch, etc. and classifies the emotions by using the statistic of the collecting data. This paper deals with the method of recognizing emotion from the sound. The most important emotional component of sound is a tone. Also, the inference ability of a brain takes part in the emotion recognition. This paper finds empirically the emotional components from the speech and experiment on the emotion recognition. This paper also proposes the recognition method using these emotional components and the transition probability.

• Journal of information and communication convergence engineering
• /
• v.19 no.3
• /
• pp.148-154
• /
• 2021

With the advent of context-aware computing, many attempts were made to understand emotions. Among these various attempts, Speech Emotion Recognition (SER) is a method of recognizing the speaker's emotions through speech information. The SER is successful in selecting distinctive 'features' and 'classifying' them in an appropriate way. In this paper, the performances of SER using neural network models (e.g., fully connected network (FCN), convolutional neural network (CNN)) with Mel-Frequency Cepstral Coefficients (MFCC) are examined in terms of the accuracy and distribution of emotion recognition. For Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset, by tuning model parameters, a two-dimensional Convolutional Neural Network (2D-CNN) model with MFCC showed the best performance with an average accuracy of 88.54% for 5 emotions, anger, happiness, calm, fear, and sadness, of men and women. In addition, by examining the distribution of emotion recognition accuracies for neural network models, the 2D-CNN with MFCC can expect an overall accuracy of 75% or more.

• Smart Media Journal
• /
• v.10 no.4
• /
• pp.21-27
• /
• 2021

Recently, the importance of counseling is increasing due to the Corona Blue caused by COVID-19. Also, with the increase of non-face-to-face services, researches on chatbots that have changed the counseling media are being actively conducted. In non-face-to-face counseling through chatbot, it is most important to accurately understand the client's emotions. However, since there is a limit to recognizing emotions only in sentences written by the client, it is necessary to recognize the dimensional emotions embedded in the sentences for more accurate emotion recognition. Therefore, in this paper, the vector and sentence VAD (Valence, Arousal, Dominance) generated by learning the Word2Vec model after correcting the original data according to the characteristics of the data are learned using a deep learning algorithm to learn the multi-dimensional We propose an emotion recognition model. As a result of comparing three deep learning models as a method to verify the usefulness of the proposed model, R-squared showed the best performance with 0.8484 when the attention model is used.

• Journal of Fashion Business
• /
• v.26 no.1
• /
• pp.1-15
• /
• 2022

Digital transformation has induced changes in human life patterns; consumption patterns are also changing to digitalization. Entering the era of industry 4.0 with the 4th industrial revolution, it is important to pay attention to a new paradigm in the fashion industry, the shift from developer-centered to user-centered in the era of the 3rd industrial revolution. The meaning of storing users' changing life and consumption patterns and analyzing stored big data are linked to consumer sentiment. It is more valuable to read emotions, then develop and distribute products based on them, rather than developer-centered processes that previously started in the fashion market. An AI(Artificial Intelligence) deep learning algorithm that analyzes user emotion big data from user experience(UX) to emotion and uses the analyzed data as a source has become possible. By combining AI technology, the fashion industry can develop various new products and technologies that meet the functional and emotional aspects required by consumers and expect a sustainable user experience structure. This study analyzes clear and useful user experience in the fashion industry to derive the characteristics of AI algorithms that combine emotions and technologies reflecting users' needs and proposes methods that can be used in the fashion industry. The purpose of the study is to utilize information analysis using big data and AI algorithms so that structures that can interact with users and developers can lead to a sustainable ecosystem. Ultimately, it is meaningful to identify the direction of the optimized fashion industry through user experienced emotional fashion technology algorithms.

• International Journal of Contents
• /
• v.8 no.1
• /
• pp.69-73
• /
• 2012

This paper aims to present colour theories and show how they can be used to explain consumer's preferences of some products over others. It will, furthermore, attempt to link these theories to the design industry and look at how colour associations determine product success. Due to associative learning and personal preference, the colours of objects can cause consumers to either favour or dislike products over those with identical functions and efficiency. Age and gender affect the preferred colour choices of the individual, making some products more popular to particular groups of potential consumers. Designers can utilise colour theories to ensure that they use the most appropriate colour schemes to maximise and appeal to their targeted market successfully. A survey was conducted with 100 participants. It demonstrates the associative links between colours, emotions and product categories. It can be shown that the colour of an object can contribute to its success or failure in the market based on a number of different criteria. The design must use colour confidently to evoke certain emotions or connotations and must be carried out appropriately. The designer also has to consider whom it is that be viewing it and making the decision of preference.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.706-708
• /
• 2023

In this study, we embark on a journey to uncover the essence of emotions by exploring the depths of transfer learning on three pre-trained transformer models. Our quest to classify five emotions culminates in discovering the KLUE (Korean Language Understanding Evaluation)-BERT (Bidirectional Encoder Representations from Transformers) model, which is the most exceptional among its peers. Our analysis of F1 scores attests to its superior learning and generalization abilities on the experimental data. To delve deeper into the mystery behind its success, we employ the powerful SHAP (Shapley Additive Explanations) method to unravel the intricacies of the KLUE-BERT model. The findings of our investigation are presented with a mesmerizing text plot visualization, which serves as a window into the model's soul. This approach enables us to grasp the impact of individual tokens on emotion classification and provides irrefutable, visually appealing evidence to support the predictions of the KLUE-BERT model.

• Journal of Venture Innovation
• /
• v.6 no.2
• /
• pp.159-172
• /
• 2023

This study aimed to empirically analyze the factors influencing the career search intention of college students. The research model was derived based on the Social Cognitive Career Theory (SCCT), considering the unique characteristics of university students. Self-efficacy and outcome expectations were investigated as independent variables, while mastery experience, verbal persuasion, vicarious learning, and positive emotions were considered as antecedent variables. A survey was conducted among college students in the metropolitan area, resulting in 217 valid responses for analysis. Empirical analysis was conducted using structural equation modeling with AMOS 24. The findings revealed that mastery experience, vicarious learning, and positive emotions had a significant positive effect on self-efficacy. Furthermore, verbal persuasion and positive emotions significantly influenced outcome expectations. However, the impact of verbal persuasion on self-efficacy was not found to be significant, and the relationship between mastery experience, vicarious learning, and outcome expectations was not examined. Both self-efficacy and outcome expectations were found to have a significant positive effect on career search intention, with outcome expectations exhibiting a stronger influence. The empirical results contribute to the understanding of college students' career exploration and provide implications for academic and practical contexts.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1184-1191
• /
• 2021

In a pop song, the creator's intention is communicated to the user through music and lyrics. Lyric meaning is as important as music, but in most cases lyrics are delivered to users in a static form without non-verbal cues. Providing lyrics in a static text format is inefficient in conveying the emotions of a music. Recently, lyrics video with kinetic typography are increasingly provided, but producing them requires expertise and a lot of time. Therefore, in this system, the emotions of the lyrics are found through the analysis of the text of the lyrics, and the deep learning model is trained with the data obtained by converting the melody into a Mel-spectrogram format to find the appropriate emotions for the music. It sets properties such as motion, font, and color using the emotions found in the music, and automatically creates a kinetic typography video. In this study, we tried to enhance the effect of conveying the meaning of music through this system.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.617-623
• /
• 2024

Identifying emotions through speech poses a significant challenge due to the complex relationship between language and emotions. Our paper aims to take on this challenge by employing feature engineering to identify emotions in speech through a multimodal classification task involving both speech and text data. We evaluated two classifiers-Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM)-both integrated with a BERT-based pre-trained model. Our assessment covers various performance metrics (accuracy, F-score, precision, and recall) across different experimental setups). The findings highlight the impressive proficiency of two models in accurately discerning emotions from both text and speech data.

• The Journal of the Korea Contents Association
• /
• v.14 no.3
• /
• pp.490-499
• /
• 2014

This research was conducted to verify the moderating effect of gender, which impacts learning strategy, negative emotions, and influence that university life adjustment of undergraduates has on academic achievement. Therefore, this survey was conducted on learning strategy and negative emotion in February, targeting 654 freshmen of a university in Seoul on their academic and social adaptation and grades which has been measured and analyzed three months later at the end of the term. The moderating effect according to genders was analyzed through hierarchical regression analyses, and diagram was presented after conducting the simple gradient verification as a post analysis on interactive effect. As a result of analysis, although learning strategy and academic adaptation was appeared to be significantly affecting grades regardless of gender, the impact of negative emotions on academic achievement were significant only to females, and the impact of social adaptation on academic achievement was significant only to males, which enabled the researchers to confirm the regulation effects on different genders. The implications and proposal for a follow-up study about learning strategy, emotion, and adaptation based on the research resulted in the discussion of academic achievement in university.