• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.163-166
• /
• 2005

We propose a speech emotion recognition method for natural human-robot interface. In the proposed method, emotion is classified into 6 classes: Angry, bored, happy, neutral, sad and surprised. Features for an input utterance are extracted from statistics of phonetic and prosodic information. Phonetic information includes log energy, shimmer, formant frequencies, and Teager energy; Prosodic information includes pitch, jitter, duration, and rate of speech. Finally a patten classifier based on Gaussian support vector machines decides the emotion class of the utterance. We record speech commands and dialogs uttered at 2m away from microphones in 5different directions. Experimental results show that the proposed method yields 59% classification accuracy while human classifiers give about 50%accuracy, which confirms that the proposed method achieves performance comparable to a human.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2002년도 추계학술대회논문초록집
• /
• pp.375.2-375
• /
• 2002

This paper describes the emotion recognition algorithm using HMM(Hidden Markov Model) method. The relation between the mechanic system and the human has just been unilateral so far This is the why people don't want to get familiar with multi-service robots. If the function of the emotion recognition is granted to the robot system, the concept of the mechanic part will be changed a lot. (omitted)

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2011년도 한국컴퓨터종합학술대회논문집 Vol.38 No.1(A)
• /
• pp.255-258
• /
• 2011

An application of Gammatone auditory filterbank for emotion recognition from speech is described in this paper. Gammatone filterbank is a bank of Gammatone filters which are used as a preprocessing stage before applying feature extraction methods to get the most relevant features for emotion recognition from speech. In the feature extraction step, the energy value of output signal of each filter is computed and combined with other of all filters to produce a feature vector for the learning step. A feature vector is estimated in a short time period of input speech signal to take the advantage of dependence on time domain. Finally, in the learning step, Hidden Markov Model (HMM) is used to create a model for each emotion class and recognize a particular input emotional speech. In the experiment, feature extraction based on Gammatone filterbank (GTF) shows the better outcomes in comparison with features based on Mel-Frequency Cepstral Coefficient (MFCC) which is a well-known feature extraction for speech recognition as well as emotion recognition from speech.

• 전기학회논문지
• /
• 제63권9호
• /
• pp.1294-1299
• /
• 2014

The emotion is deeply affected by human behavior and cognitive process, so it is important to do research about the emotion. However, the emotion is ambiguous to clarify because of different ways of life pattern depending on each individual characteristics. To solve this problem, we use not only physiological signal for objective analysis but also hybrid unsupervised-supervised learning classifier for automatic emotion detection. The hybrid emotion classifier is composed of K-means, genetic algorithm and support vector machine. We acquire four different kinds of physiological signal including electroencephalography(EEG), electrocardiography(ECG), galvanic skin response(GSR) and skin temperature(SKT) as well as we use 15 features extracted to be used for hybrid emotion classifier. As a result, hybrid emotion classifier(80.6%) shows better performance than SVM(31.3%).

• 정보화연구
• /
• 제9권3호
• /
• pp.333-344
• /
• 2012

본 논문에서는 개인의 취향과 관심이 반영 되어있는 소셜 정보를 활용하여 사용자에게 영화를 추천할 수 있는 시스템을 제안하였다. 시스템에서 데이터 구축은 포털사이트에서 영화 정보를 수집하고 페이스북과 트위터 같은 SNS를 통해 소셜 정보를 수집한다. 본 논문에서는 사용자의 감정에 따른 보다 정교한 처리를 위하여 6단계의 감정단계로 분류한 소셜 정보의 벡터공간 모형의 구축방법을 제안한다. 추천을 위한 유사도 측도 방법은 2단계로 구성되어 있다. 첫 번째는 일반적인 코사인 측도를 통한 영화 목록의 구축 단계이고, 두 번째는 기존의 코사인 측도(Cosine measure)를 활용한 좌표평면에서 감정 단계별 벡터 정보 표현 방법 및 유사도 측도 방법을 통해 추천 영화 목록의 결정 단계이다. 본 논문의 추천 시스템의 성능을 평가하기 위하여 기존의 추천 시스템과 비교 실험을 통하여 본 연구의 추천 시스템의 유용성을 검증하였다.

• 한국멀티미디어학회논문지
• /
• 제18권2호
• /
• pp.233-243
• /
• 2015

A hotspot is a spatial pattern that properties or events of spaces are densely revealed in a particular area. Whereas location information is easily captured with increasing use of mobile devices, so is not our emotion unless asking directly through a survey. Tweet provides a good way of analyzing such spatial sentiment, but relevant research is hard to find. Therefore, we analyzed hotspots of emotion in the twitter using spatial autocorrelation. 10,142 tweets and related GPS data were extracted. Sentiment of tweets was classified into good or bad with a support vector machine algorithm. We used Moran's I and Getis-Ord $G_i^*$ for global and local spatial autocorrelation. Some hotspots were found significant and drawn on Seoul metropolitan area map. These results were found very similar to an earlier conducted official survey of happiness index.

• 한국정보전자통신기술학회논문지
• /
• 제5권1호
• /
• pp.45-51
• /
• 2012

본 논문은 사용자의 생체 정보(맥박, 이완기 혈압, 수축기 혈압, 혈당)를 무선 센서들을 통하여 획득한 후 스트레스 지수에 따른 감성을 인식하여 대응되는 컬러와 음원을 분류하는 시스템으로서, 맥박 센서, 혈압 센서, 혈당 센서 등의 입력치를 받아 데이터베이스에 저장한 후 다중 SVM(Support Vector Machine) 알고리즘을 이용하여 스트레스 지수에 따른 감성을 분류한다. 2,000개의 데이터 집합을 사용하여 다중 SVM 알고리즘을 학습한 결과 약 87.7%의 정확도를 가졌다.

• 대한인간공학회지
• /
• 제30권6호
• /
• pp.705-713
• /
• 2011

Objective: The aim of this study is to compare results of emotion recognition by several algorithms which classify three different emotional states(happiness, neutral, and surprise) using physiological features. Background: Recent emotion recognition studies have tried to detect human emotion by using physiological signals. It is important for emotion recognition to apply on human-computer interaction system for emotion detection. Method: 217 students participated in this experiment. While three kinds of emotional stimuli were presented to participants, ANS responses(EDA, SKT, ECG, RESP, and PPG) as physiological signals were measured in twice first one for 60 seconds as the baseline and 60 to 90 seconds during emotional states. The obtained signals from the session of the baseline and of the emotional states were equally analyzed for 30 seconds. Participants rated their own feelings to emotional stimuli on emotional assessment scale after presentation of emotional stimuli. The emotion classification was analyzed by Linear Discriminant Analysis(LDA, SPSS 15.0), Support Vector Machine (SVM), and Multilayer perceptron(MLP) using difference value which subtracts baseline from emotional state. Results: The emotional stimuli had 96% validity and 5.8 point efficiency on average. There were significant differences of ANS responses among three emotions by statistical analysis. The result of LDA showed that an accuracy of classification in three different emotions was 83.4%. And an accuracy of three emotions classification by SVM was 75.5% and 55.6% by MLP. Conclusion: This study confirmed that the three emotions can be better classified by LDA using various physiological features than SVM and MLP. Further study may need to get this result to get more stability and reliability, as comparing with the accuracy of emotions classification by using other algorithms. Application: This could help get better chances to recognize various human emotions by using physiological signals as well as be applied on human-computer interaction system for recognizing human emotions.

• 전기학회논문지
• /
• 제67권11호
• /
• pp.1496-1505
• /
• 2018

The technology of emotion recognition is necessary for human computer interaction communication. There are many cases where one cannot communicate without considering one's emotion. As such, emotional recognition technology is an essential element in the field of communication. n this regard, it is highly utilized in various fields. Various bio-sensor sensors are used for human emotional recognition and can be used to measure emotions. This paper proposes a system for recognizing human emotions using two physiological sensors. For emotional classification, two-dimensional Russell's emotional model was used, and a method of classification based on personality was proposed by extracting sensor-specific characteristics. In addition, the emotional model was divided into four emotions using the Support Vector Machine classification algorithm. Finally, the proposed emotional recognition system was evaluated through a practical experiment.

• 한국컴퓨터정보학회논문지
• /
• 제18권9호
• /
• pp.131-138
• /
• 2013

본 논문에서는 등장인물이 대사에서사용한감정어를 이용하여 등장인물의 감정 유형을 분류하는 방법을 제안하고 성능을 평가한다. 감정 유형은 긍정, 부정, 중립의 3 종류로 분류하며, 등장인물이 사용한 감정어를 누적하여 3 종류의 감정 유형 중에 어디에 속하는지를 파악한다. 대사로부터 감정어를 추출하기 위해 WordNet 기반의 감정어 추출 방법을 제안하고 감정어가 가진 감정 성분을 벡터로 표현하는 방식을 제안한다. WordNet은 영어 단어 간에 상위어와 하위어, 유사어 등의 관계로 연결된 네트워크 구조의 사전이다. 이 네트워크 구조에서 최상위의 감정항목과의 거리를 계산하여 단어별감정량을 계산하여 대사를 30 차원의 감정벡터로 표현한다. 등장인물별로 추출된 감정 벡터 성분들을 긍정, 부정, 중립의 3가지 차원으로 축소하여 표현한 후, 등장인물의 감정 성향이 어떻게 나타나는지를 추출한다. 또한 감정 성향의 추출 성능에 대해 헐리우드 영화 4개의 영화에서 12명의 등장인물을 선정하여 평가하여 제안한 방법의 효율성을 측정하였다. 대사는 영어로 이루어진 대사만을 사용하였다. 추출된 감정 성향 판단 성능은 75%의 정확도로 우수한 추출 성능을 나타내었다.