• 전기학회논문지
• /
• 제66권7호
• /
• pp.1105-1110
• /
• 2017

Speech with various emotions degrades the performance of the speaker recognition system. In this paper, a speaker recognition method using emotional adaptation has been proposed to improve the performance of speaker recognition system using affective speech. For emotional adaptation, emotional speaker model was generated from speaker model without emotion using a small number of training affective speech and speaker adaptation method. Since it is not easy to obtain a sufficient affective speech for training from a speaker, it is very practical to use a small number of affective speeches in a real situation. The proposed method was evaluated using a Korean database containing four emotions. Experimental results show that the proposed method has better performance than conventional methods in speaker verification and speaker recognition.

• 감성과학
• /
• 제14권3호
• /
• pp.371-384
• /
• 2011

LED 조명의 색상이 정서자극의 평정과 재인에 어떤 영향을 미치는지를 알아보기 위하여 세 개의 실험을 실시하였다. 실험 1과 2에서는 IAPS 정서사진을 사용하여 각각 Red, Green, Blue, 및 White와 Cyan, Magenta, Yellow, 및 White의 조명색상조건에서 정서평정(정서가, 각성차원) 과제와 재인기억과제를 실시하였다. 실험 3에서는 정서단어를 사용하여 Red, Green, Blue, 및 White 조명색상조건에서 두 과제를 실시하였다. 실험 결과, 정서평정과제에서는 일차 색상(RGB)의 경우, LED조명 색상이 Red일 때는 흥분을, Green일 때는 유쾌 정서를 유발하였고, 이차 색상(CMY)의 경우, Magenta와 Cyan은 Red와 Green과 유사한 패턴의 정서 반응을 유발하였으나 그 강도는 약하였다. 재인기억과제에서는 실험 1과 실험 2의 경우, Green과 Cyan 조명색상조건에서 제시되었던 사진자극들에 대한 반응이 다른 조명색상조건에서 제시되었던 사진자극들에 비해 약간 빠른 경향이 있었으나 유의미한 차이는 아니었다. 하지만 실험 3에서는 Green 조명색상조건에서 제시되었던 정서단어들에 대한 재인기억반응이 유의미하게 빨랐다. 이러한 결과로 Red나 Magenta와 같은 난색들은 불쾌나 흥분과 관련된 감성을 유발하는 반면, Green이나 Cyan과 같은 한색들은 유쾌나 이완과 같은 감성을 유발하는 경향이 있으며, 일차 색상들이 이차 색상들보다 강한 정적 내지 부적 감성을 유발함을 알 수 있다. 특히 실험 3의 재인 기억과제에서 나타난 결과는 시각 자극보다 언어 자극의 기억수행에 Green 색상의 LED 조명이 더 유리함을 시사한다.

• Journal of Computing Science and Engineering
• /
• 제10권4호
• /
• pp.103-110
• /
• 2016

Emotion recognition is an important component of affective computing, and is significant in the implementation of natural and friendly human-computer interaction. An effective approach to recognizing emotion from text is based on a machine learning technique, which deals with emotion recognition as a classification problem. However, in emotion recognition, the texts involved are usually very short, leaving a very large, sparse feature space, which decreases the performance of emotion classification. This paper proposes to resolve the problem of feature sparseness, and largely improve the emotion recognition performance from short texts by doing the following: representing short texts with word cluster features, offering a novel word clustering algorithm, and using a new feature weighting scheme. Emotion classification experiments were performed with different features and weighting schemes on a publicly available dataset. The experimental results suggest that the word cluster features and the proposed weighting scheme can partly resolve problems with feature sparseness and emotion recognition performance.

• 인터넷정보학회논문지
• /
• 제12권6호
• /
• pp.83-94
• /
• 2011

감정 컴퓨팅의 대표적 연구 주제는 기계가 사람의 감정을 인식하여 이에 적절히 대응하는 것이다. 감정 인식 연구에서는 얼굴과 목소리 단서를 이용하여 감정을 포착하는데 집중했으며 최근에 와서 행동자세를 주요 수단으로 이용하고 있다. 본 연구의 목적은 감정 표현에서 중요한 역할을 담당하는 자세 특징을 포착하고 확인하여 감정을 판별하는 것이다. 이를 위해 먼저 자세포착시스템으로 다양한 감정 자세를 수집하여 감정별 특징을 공간적 특징으로 설명한다. 그리고 동작을 취하는 행위자가 의도하는 감정과 관찰자가 인지하는 감정 간에 통계적으로 의미 있는 상관관계가 있음을 표준통계기술을 통해 확인한다. 6가지 주요 감정을 판별하기 위해 판별 분석법을 이용하여 감정 자세 예측 모델을 구축하고 자세 특징을 측정한다. 제안 특징과 모델의 평가는 행위자-관찰자 감정 자세 집단의 상관관계를 이용하여 수행한다. 정량적 실험 결과는 제안된 자세 특징으로 감정을 잘 판별하며 감정 예측 모델이 잘 수행됨을 보여준다.

• 아동학회지
• /
• 제6권2호
• /
• pp.59-71
• /
• 1985

The purpose of this study was to analyze the effects of both social-status and mode of stimulus-presentation on children's empathic behavior, where empathy is defined as either the comprehension and recognition of an affective state in stimulus persons (others) or the empathic response to that perception. Middle-and lower-class kindergarten children were presented with a series of either short-sentence stories or short-pictorial stories. The subjects were asked to indicate how the child in each situation felt by selecting a "happy", "sad", or "angry" face to complete the picture accompanying each story. Immediately following the first question, children were asked to state verbally how the child in the picture might feel. The main results were (1) The mean empathy scores for the comprehension and recognition of an affective state in others and the empathic response to that perception was higher in middle-class children than in lower-class children. (2) There were differences in empathy scores to the three affective situations, i.e. the mean score for both happiness and sadness was significantly greater than for aggression, and (3) The empathy scores in the pictorial-stories were greater than in the sentence-stories.

• 한국학교수학회논문집
• /
• 제19권1호
• /
• pp.83-102
• /
• 2016

본 연구에서는 수학과 독서를 활용한 수학 수업이 학생들에게 정의적으로 어떠한 영향을 미치는지 탐구하였다. 중학교 2학년 100명의 남학생을 대상으로 정의적 특성요소로 흥미, 자신감, 가치인식, 자기조절력, 수학 불안 5개 요인을 조사해보고, 상 중 하 수준별 학생들에게 수학과 독서수업이 미치는 영향을 탐구하였다. 또 사전 사후 검사 결과와 학생의 인터뷰를 통해 바람직한 독서를 활용한 수업 방안을 모색하였다.

• 한국프랜차이즈경영연구
• /
• 제12권3호
• /
• pp.47-58
• /
• 2021

Purpose: In general, franchise business models can generate higher returns and profits than non-franchise businesses. Therefore, it is necessary to study customer-based foodservice franchise brand awareness and service quality. The purpose of this study is to investigate the effect of service quality and brand awareness of foodservice franchises on attitudes divided into cognitive and affective attitudes and revisit intentions. Through this study, we intend to establish a structure that leads to service quality and brand awareness-cognitive attitude and affective attitude-loyalty. Research design, data, and methodology: In order to verify the hypothesis of this study, the survey was conducted among general consumers over the age of 20 who had visited a foodservice franchise within the last 3 months. Among the collected questionnaires, one insincere questionnaire was excluded, and 299 copies were used for analysis. The data collected to verify the hypothesis of this study were analyzed using SPSS 24.0 and AMOS 24.0. Result: First, it was found that the service quality of the foodservice franchise had a positive (+) effect on the cognitive attitude, and the service quality of the foodservice franchise had a statistically significant positive effect on the affective attitude. Second, the brand awareness of the foodservice franchise was found to have a statistically significant positive (+) effect on the cognitive attitude. and the brand awareness of the foodservice franchise had a statistically significant positive (+) effect on the affective attitude as well. Third, cognitive attitude was found to have a statistically significant positive (+) effect on loyalty, and affective attitude was also found to have a statistically significant positive (+) effect on loyalty. Conclusions: First, this study applied the S-O-R theory to the effect of service quality and brand recognition on cognitive attitude, affective attitude, and loyalty. Second, the structure leading to service quality and brand awareness-cognitive attitude and affective attitude-revisit intention was established. Third, attitudes in this study were divided into cognitive attitudes and affective attitudes. In general, attitude is studied as a single dimension as a cognitive attitude, but in this study, attitude was studied by dividing it into a cognitive dimension and an affective dimension

• 생물정신의학
• /
• 제12권2호
• /
• pp.207-215
• /
• 2005

Objectives:This study was to compare verbal memory ability among patients with schizophrenia, bipolar manic patients and unipolar depressive patients, and to understand their charicteristics of memory process. Methods:All subjects were hospitalized patients and had been interviewed by using the Structured Clinical Interview for DSM-IV(SCID). Schizophrenic patients(N=40), bipolar manic patients(N=17), and unipolar depressive patients(N=20) were assessed with K-AVLT for verbal memory and with K-WAIS for verbal IQ. Three groups were compared regarding total immediate recall, delayed recall, delayed recognition, learning curve, memory retention, and retrieval efficiency under controlled verbal IQ. Multiple regression analysis was performed to find which clinical factors have an influence on verbal memory ability. Results:In MANCOVA, differences of verbal memory test scores among the groups were statistically significant(F=1.800, p<.05). In post hoc analysis, Patients with schizophrenia and bipolar mania showed poorer performance in immediate recall, delayed recall, delayed recognition, retrieval efficiency than unipolar depres- sive patients. And schizophrenics performed poorly in delayed recall, delayed recognition, retrieval efficiency than nonpsychotic affective disorder group, but no difference in total immediate recall, delayed recall, delayed recognition, retrieval efficiency between the schizophrenic group and the psychotic affective group. Conclusions:These results partially confirm previous reports of verbal memory ability among major psychiatric disorders. Our results showed that psychotic symptoms were related with verbal memory, and longer duration of illness was related with poorer performance in schizophrenia and unipolar depression.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.369-376
• /
• 2021

One of the most active areas of research in the field of affective computing and signal processing is emotion recognition. This paper proposes emotion recognition of low-resource (Sindhi) language. This work's uniqueness is that it examines the emotions of languages for which there is currently no publicly accessible dataset. The proposed effort has provided a dataset named MAVDESS (Mehran Audio-Visual Dataset Mehran Audio-Visual Database of Emotional Speech in Sindhi) for the academic community of a significant Sindhi language that is mainly spoken in Pakistan; however, no generic data for such languages is accessible in machine learning except few. Furthermore, the analysis of various emotions of Sindhi language in MAVDESS has been carried out to annotate the emotions using line features such as pitch, volume, and base, as well as toolkits such as OpenSmile, Scikit-Learn, and some important classification schemes such as LR, SVC, DT, and KNN, which will be further classified and computed to the machine via Python language for training a machine. Meanwhile, the dataset can be accessed in future via https://doi.org/10.5281/zenodo.5213073.

• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.603-623
• /
• 2023

While prior work has conducted individuals' password security behavior, there is a relatively neglect to examine individuals' affect and feelings of password fatigue in password change context. Therefore, this study explicated individuals' affective response to the feelings of password fatigue by drawing on several theoretical lens. Survey data collected from 267 users were used to test the model using partial least square analysis. This study found that feelings of password fatigue positively affected the negative password fatigue-induced affect, and also both the feelings of password fatigue and the negative password fatigue-induced affect were negatively related to attitude toward changing passwords, which in turn, leads to the intention to change passwords. Furthermore, this study found that shadow work recognition negatively moderated the relationship between attitude and behavioral intention. This study could offer a new theoretical perspective to understand an individual's security behavior and provide empirical evidences for practitioners in charge of IT security in organizations.