• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1370-1376
• /
• 2012

This paper proposes a gender recognition algorithm which classifies a male or female speaker. In this paper, characteristic vectors for the male and female speaker are analyzed, and recognition experiments for the proposed gender recognition by a neural network are performed using these characteristic vectors for the male and female. Input characteristic vectors of the proposed neural network are 10 LPC (Linear Predictive Coding) cepstrum coefficients, 12 LPC cepstrum coefficients, 12 FFT (Fast Fourier Transform) cepstrum coefficients and 1 RMS (Root Mean Square), and 12 LPC cepstrum coefficients and 8 FFT spectrum. The proposed neural network trained by 20-20-2 network are especially used in this experiment, using 12 LPC cepstrum coefficients and 8 FFT spectrum. From the experiment results, the average recognition rates obtained by the gender recognition algorithm is 99.8% for the male speaker and 96.5% for the female speaker.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.919-921
• /
• 2004

본 논문은 사람 이름의 특성을 이용한 이름 인식과 이름의 성별 구분 방법에 대해 제안한다 사랑 이름을 묻는 질의문은 질의-응답 시스템에서 자주 나타난다. 모든 사람 이름을 사전에 등록하는 것은 어렵다. 경우에 따라서는 남녀 이름을 구분할 필요가 있다. 한국 사람 이름의 특성은 주로 3음절로 이루어져 있고. 성씨로 사용되는 음절의 수가 제한적이라는 것이다. 또한 이름에는 한자 독음이 많이 쓰이고, 남자 이름으로 자주 쓰이는 음절과 절자 이름으로 자주 쓰이는 음절이 있다. 이러한 특성을 이용하여 사람 이름 인식과 성별 구분을 수행한다. 일반 웹 문서에서의 실험 결과, 이름 인식의 정확률은 94%를 보였고, 남녀 이름 구분의 정확률은 98%를 보였다.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.155-156
• /
• 2015

본 연구는 의료기관에서 근무하는 방사선사를 고용형태를 중심으로 구분하여, 정규직과 비정규직 간의 인식차이, 이직의도, 직무스트레스, 심리적 상태의 관계를 알아보고자 실시하였다. 연구 대상은 수도권역과 지방권역으로 9개 의료기관에서 종사하는 방사선사 308명으로 하였다. 2012년 7월 18일에서 9월 15일까지 수집된 설문지를 통계적으로 분석하여 다음과 같은 연구 결과를 얻었다. 정규직과 비정규직 방사선사의 인식차이에서 정규직은 성별, 월 급여, 지역권에서 유의한 차이가 있었다. 이직의도는 정규직에서 학력, 월 급여, 지역권에서 그리고 비정규직은 성별에서만 유의한 차이가 있었다. 직무스트레스는 정규직에서 학력, 월 급여, 지역권에서와 비정규직은 성별, 나이, 결혼, 총 직장 근무연수에서 유의한 차이가 있었다. 심리적 상태에서 정규직은 성별에서와 비정규직은 성별, 결혼에서 유의한 차이가 있었다. 정규직, 비정규직 간의 직무적 요인에 대한 상관관계에서 인식차이는 이직의도와 심리적 상태에서, 이직의도는 인식차이와 직무스트레스 및 심리적 상태에서, 직무스트레스는 이직의도와 심리적 상태에서, 심리적 상태는 인식차이, 이직의도 및 직무스트레스에서 유의하였다. 고용형태에 따른 요인별 직무스트레스에서는 직무요구 요인, 직무자율성 요인, 관계갈등 요인, 직무불안정 요인에서 유의한 차이가 있었다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.4
• /
• pp.107-114
• /
• 2008

In this paper, we constructed a speech emotion recognition system that classifies four emotions - neutral, happy, sad, and anger from speech based on male/female gender discrimination. At first, the proposed system distinguish between male and female from a queried speech, then the system performance can be improved by using separate optimized feature vectors for each gender for the emotion classification. As a emotion feature vector, this paper adopts ZCPA(Zero Crossings with Peak Amplitudes) which is well known for its noise-robustic characteristic from the speech recognition area and the features are optimized using SFS method. For a pattern classification of emotion, k-NN and SVM classifiers are compared experimentally. From the computer simulation results, the proposed system was proven to be highly efficient for speech emotion classification about 85.3% regarding four emotion states. This might promise the use the proposed system in various applications such as call-center, humanoid robots, ubiquitous, and etc.

• Proceedings of The KACE
• /
• 2018.08a
• /
• pp.113-116
• /
• 2018

SW 교육은 SW 산업의 여성 인력 확대를 위하여 여성에게 알맞은 방식으로 도입 및 개선될 필요가 있다. 여성에게 적합한 교육을 찾기 위해서는 성별에 따라 SW를 인식하는 차이에 대한 연구가 선행되어야 한다. 본 연구는 'SW 개념 인지도'와 'SW 흥미도' 두 관점을 통해 성별에 따른 SW 인식 차이를 규명하였다. 그 결과, SW 개념을 인지 하게 된 경로는 비슷하며 SW 교육을 경험해 본 비율은 여학생보다 남학생이 많은 것을 알 수 있었다. 또한, 남학생이 여학생보다 SW 활동에 더 자신감과 흥미를 느끼는 것으로 나타났으며 희망하는 SW 교육방법에서도 성별에 따른 차이가 있음을 알 수 있었다. 본 연구 결과를 토대로 각 성별에 알맞은 교수학습 등을 연구하는데 도움이 될 것으로 사료된다.

• Journal of Industrial Convergence
• /
• v.21 no.2
• /
• pp.79-84
• /
• 2023

This study was analyzed based on 1051 analyzes of questionnaires in order to examine the status and perception of abused drugs according to the gender of the young people entering the adult group from the adolescents. The gender of the young people who participated in the survey was 686 males and 365 females, and the types of abused drugs and their perceptions of harmful effects of narcotics and abused drugs were analyzed according to gender. As a result of the study, the experience of using alcohol, tobacco, appetite suppressants, sedatives, and opioid analgesics was statistically significant according to gender. Among the harmful effects of narcotic drugs and drugs of abuse, significant results were shown on the recognition of risks, induced problems, and sympathy for risks. As for the desirable way to improve the problem of narcotics and substance abuse, 257 women (68.2%) of women wanted publicity (enlightenment) activities, and about effective education for preventing narcotics and substance abuse, 379 men (54.2%) of men %) appeared as online online education. It is considered that proper education and publicity about drug use is necessary in the reality that drug addiction among young people due to drug abuse is increasing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.4
• /
• pp.775-780
• /
• 2013

This paper proposes a speaker-dependent speech recognition algorithm which can classify the gender for male and female speakers in white noise and car noise, using a neural network. The proposed speech recognition algorithm is trained by the neural network to recognize the gender for male and female speakers, using LPC (Linear Predictive Coding) cepstrum coefficients. In the experiment results, the maximal improvement of total speech recognition rate is 96% for white noise and 88% for car noise, respectively, after trained a total of six neural networks. Finally, the proposed speech recognition algorithm is compared with the results of a conventional speech recognition algorithm in the background noisy environment.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.455-458
• /
• 2000

인공 신경망은 체계적인 알고리즘으로 풀기 어려운 문제들을 해결하는데 사용되어오고 있다. 이는 인간의 뇌세포가 외부자극에 대해 반응하는 과정을 컴퓨터 시스템 상에서 구현한 것으로 새 인간과 컴퓨터의 상호작용을 연구하는데 흥미로운 접근방식이다. 본 논문에서는 신경망의 접근방법을 이용하여 인간행위 인식시스템을 구현하였다. 신경망을 이용해 구현된 컴퓨터 인식 시스템이 인간의 두 가지 정서 하에서 일어난 세가지 서로 다른 행동을 보고 행위자의 성별이나 강정상태를 얼마나 인식해낼 수 있는지 실험해 보았다. 특히, 성별 인식 실험에서는 신호탐지 이론에서 사용하는 인장도(discriminability)를 이용해 사람에 대한 이 시스템의 효율도를 계산하였다

• The Journal of the Korea Contents Association
• /
• v.9 no.8
• /
• pp.423-432
• /
• 2009

This paper focuses on gender studies with respect to language education for KFL(Korean as a foreign language) students. It also attempts to view the role of gender as exerting influence on language learning and teaching, and surveys KFL teachers' awareness of the role of gender in Korean language education. It is conceivable that teachers who are aware of differences between female and male will be able to take these into account in their teaching; in doing so they will be more effective in their teaching than if they were to teach in ignorance of these differences. The survey for the teachers' awareness of gender difference was conducted through teachers' discussion as the follow-up measure of the questionnaire. A few teachers do not have a clear idea about the importance of gender differences in language teaching, but the majority have cognizance of the matter. For this research, a questionnaire was administered to 71 subjects, consisting 37 intermediate KFL students and 34 advanced KFL students. The result of the questionnaire reveals that 50.4% subjects use their words and intonation without recognizing the gender difference, on the other hand, 49.6% subjects recognize the gender differences in Korean language use. The result should be adopted as a sociolinguistic factor for the contents of second language education.

• The Korean Journal of Elementary Counseling
• /
• v.11 no.2
• /
• pp.171-192
• /
• 2012

This study examined the aspects in elementary school students' career interest and career awareness by gender, age, and multi-cultural families/general families. The subjects were 341 elementary school students from multi-cultural families and general families. The results were as follows. First, there were significant differences in investigative, artistic, and social interests by gender. The children from multi-cultural families and general families showed no significant differences in career interest. Second, the children from general families had higher scores than those from multi-cultural families in self-awareness, occupational exploration, career attitude, and career awareness. And the girls had higher scores than boys in self-awareness, occupational exploration, and career awareness. Third, there were meaningful differences in career interest and career awareness by age. The younger children had higher scores in career interest and lower scores in career awareness. Fourth, the career interests had significant correlations with career awareness in both groups. And there were stronger correlations in general children. Fifth, the regression analyses showed that career interests had significant effects on career awareness in both groups, and there were higher effects in general children. The artistic interests in multi-cultural children and the social interest in general children had significant effects on career awareness. And the effect of multi-cultural families/general families was noticeable in occupational exploration, career attitude, and career awareness. The implication for multi-cultural career education and counseling practice are discussed based on the result of the present study.