[특집] 유비쿼터스 환경의 정보서비스를 위한 음성기술 표준화 동향

홍기형(Ki-Hyung Hong),정민화(Minhwa Chung) 한국정보과학회 2006 정보과학회지 Vol.24 No.1

퇴직교원의 교육요구에 관한 기초연구

홍기형(Ki Hyung Hong),나항진(Hang Jin Na) 한국노인복지학회 2000 노인복지연구 Vol.8 No.-

The purpose of this study is to identify the Needs of Teachers for retirement education. That purpose was intended to provide practical alternatives which solve the problems concerning with retirements and aging. Consequences of this study in part, will be contributed to minimize the problem that shortened the period of appointment of teachers. We just don`t demand retirement of teachers, but we can provide the environments which cut one`s new way after retirement by providing the programs for increasing the welfare of teachers. Findings follow. 1. Quite a few of Teachers was considerated to retire from the office before the period of appointment. After retirement, they want to get their leisure and voluntary services rather than to get other jobs. 2. they want to get retirement education in universities or educational institutes which are located near their houses. 3. Most teachers think that universities or educational institutes for teachers should be in charge of retirement education and expenses needed for education. 4. The contents of refit education for teachers should include the programs that would help teachers make comportable and healthy living. And they want leasure activities which don`t have special purposes. They want to get health information, hobbies, technical abilities for perfect harmony in life, information technology education etc. 5. The determitants for the success of programs include education contents, the amount of charges for education, distance from house to educational institute. To develop the process of educational programs, there should be systematic research which back up. There also should be information warehouse that help practically carry out the progratns. In conclusion, we must consider retiring teachers of the public resources.

노인의 학습 요구분석에 관한 연구

홍기형(Ki Hyung Hong),나항진(Hang Jin Na) 한국노인복지학회 2002 노인복지연구 Vol.17 No.-

본 연구를 통하여 다음과 같은 사실을 확인할 수 있었다. 즉, 중하위 계층 노인들을 대부분 학습 즉 교육이 필요하다고 인식하고 있었으며, 학습에 참여하고 있는 노인들의 경우에는 그들에게 닥친 당면 문제를 해결하려는 목적으로 교육에 참여하는 것으로 조사되었다. 물론 성이나 연령, 학력에 따라서 당면한 문제가 다를지라도 이를 해소하기 위해서 교육기관을 찾는 것으로 조사되었다. 이는 이들이 받고 싶은 교육내용으로 연결되어 요구로 표출되고 있었으며, 노후를 즐겁게 생활하기 위하여 기초교육부터 재취업교육에 이르기까지 그들이 처한 상황에 따라 다양한 교육적인 요구를 지닌 것으로 조사되었다. 다양한 요구를 수렴하기 위한 다양한 프로그램의 개발, 전문적인 프로그램을 제공하는 노인교육기관이 설립되어야 할 것이다. It was found in this study that the elderly from the middle and lower classes were cognizant of their need for education and that the old learners participating in the learning program did that in order to solve the problems they were faced with. Despite the fact that problems may be different in proportion to their set age, education etc., they took part in the educational program for the purpose of solving their problems. It was also found that they expressed their needs for appropriate teaming programs, ranging from basic education to re-employment skill acquisition to make their last stage of life happier. It should be suggested that the authorities should develop a variety of programs and educational facilities for them.

음성기반 멀티모달 인터페이스 및 표준

홍기형,Hong Ki-Hyung 대한음성학회 2004 말소리 Vol.51 No.-

In this paper, we introduce the multimodal user interface technology, especially based on speech. We classify multimodal interface technologies into four classes: sequential, alternate, supplementary, and semantic multimodal interfaces. After introducing four types of multimodal interfaces, we explain standard activities currently being activated.

효율적인 순환 질의 처리를 위한 적절한 Wavefront의 사용

홍기형(Ki Hyung Hong),이윤준(Yoon Joon Lee) 한국정보과학회 1987 한국정보과학회 학술발표논문집 Vol.14 No.1

연역 데이타베이스 시스템에어 순환 질의의 처리는 매우 중요하다. 그 이유는 순환 질의 처리 과정에서 많은 연산이 반복적으로 수행될 뿐 아니라 각 단계의 반복에서 많은 양의 자료를 검색하고 추출하여야 하기 때문이다. Wavefront의 사용은 이러한 순환 질의 처리 과정에서 같은 연산의 중복을 방지하여 효과적인 처리가 가능하도록 한다. 그러나 한 가지 형태의 wavefront만을 사용하는 경우에는 더 많은 중복 연산을 피할 수 있음에도 어떤 질의에 대하여는 그렇지 못한 상황이 발생한다. 본 연구에서는 순환 규칙의 형태와 각 질의에 포함되어 있는 선택 연산의 위치에 따라 같은 연산의 중복을 최대한 방지할 수 있도록 wavefront를 선택하여 보다 효과적인 순환 질의의 처리가 가능하도록 하였다.

음성기반 멀티모달 사용자 인터페이스의 사용성 평가 방법론

홍기형,Hong, Ki-Hyung 대한음성학회 2008 말소리 Vol.67 No.-

Basic components for multimodal interface, such as speech recognition, speech synthesis, gesture recognition, and multimodal fusion, have their own technological limitations. For example, the accuracy of speech recognition decreases for large vocabulary and in noisy environments. In spite of those technological limitations, there are lots of applications in which speech-oriented multimodal user interfaces are very helpful to users. However, in order to expand application areas for speech-oriented multimodal interfaces, we have to develop the interfaces focused on usability. In this paper, we introduce usability and user-centered design methodology in general. There has been much work for evaluating spoken dialogue systems. We give a summary for PARADISE (PARAdigm for Dialogue System Evaluation) and PROMISE (PROcedure for Multimodal Interactive System Evaluation) that are the generalized evaluation frameworks for voice and multimodal user interfaces. Then, we present usability components for speech-oriented multimodal user interfaces and usability testing guidelines that can be used in a user-centered multimodal interface design process.

Development and Usability Testing of a SpeechTechnology based Face-to-Face Mobile Communication Application for People with Hearing Impairments

홍기형(Ki Hyung Hong),이희연(Hee yeon Lee) 한국언어청각임상학회 2017 Communication Sciences and Disorders Vol.22 No.2

배경 및 목적: 본 연구의 목적은 청각장애인과 건청인 대화 상대자가 일상에서 대면 의사소통을 할 때 경험하는 어려움과 의사소통 지원요구를 파악하고, 음성기술에 기반하여 의사소통 지원요구들을 반영한 청각장애인용 대면 의사소통 앱을 구현하며, 실제 사용자인 청각장애인을 대상으로 개발된 의사소통 앱의 사용성을 평가하는 것이다. 방법: 기존의 청각장애인용 의사소통 앱 분석, 청각장애인의 의사소통 능력별 음성기술 요구분석, 관련 선행연구 분석, 언어장애인용 앱의 청각장애인 사용자 면담 등을 통하여 청각장애인과 건청인의 대면 의사소통 상황에서 요구되는 기능들을 파악하고 이를 반영한 음성기술 기반 의사소통 앱을 개발한 후 총 25명의 청각장애인을 대상으로 시나리오와 설문지를 통한 사용성 평가를 실행하였다. 결과: 연구결과, 단어자동완성, 즐겨 찾기와 빈도수, 장문 합성, 상황 별 대화 문장 등록, 예상 대화문장 제시 등의 기능 요구가 도출되었다. 이를 반영하여 개발한 대면 의사소통 앱에 대한 사용성 평가를 실시한 결과 앱 개발의 타당성, 사용편의성, 만족도, 활용도, 기여도 등에서 5점 척도를 기준으로 전체 평균 4점(대체로 그렇다) 이상의 긍정적인 평가를 받았다. 논의 및 결론: 본 연구에서 개발된 음성기술 기반 대면 의사소통 앱이 청각장애인과 건청인의 대면 의사 소통을 증진시킴으로써 청각장애인의 활동참여 및 삶의 질을 증진하는 데 기여하고, 후속 연구로 언어 및 청각장애인을 위한 다양한 국내모바일의사소통도구들의개발이이루어지기를기대한다. Objectives: The purpose of this study was to identify difficulties and support requirements experienced by people with hearing impairments in daily communication with their hearing communication partner, to develop a speech-technology based face-to-face mobile communication application based on their needs, and to evaluate the necessity and validity, ease of use, satisfaction, and utilization of the application by conducting usability tests. Methods: This study investigated the functionality of the mobile communication application for people with hearing impairments by examining current mobile communication applications and by reviewing previous literature. We then developed a speech-technology based face-to-face mobile communication application reflecting the required functions. In order to evaluate the usability of the face-to-face mobile communication application, usability tests comprised of scenarios and survey questionnaires were conducted with 25 people with hearing impairments. Results: The results of this study showed the usability of the developed speech-technology based face-to-face mobile communication application was positive (above 4 on the 5-point Likert scale) in terms of feasibility, userfriendliness, satisfaction, and utilization. Conclusion: It is expected that the developed mobile communication application will help improve social participation and quality of life for people with hearing impairments. It is also expected that the development of various domestic mobile communication devices for people with hearing impairments or language disorders will be promoted.

동적 규칙 적용 순서에 의한 Semi-Naive 순환 질의 처리 방법

홍기형(Ki-Hyung Hong),이윤준(Yoon-Joon Lee),황규영(Kyu-Young Whang) 한국정보과학회 1996 정보과학회논문지(B) Vol.23 No.4

본 논문에서는, 새로운 상향식 순환 처리방법으로 규칙의 적용 순서를 실행 시점에 결정하는 동적 규칙 적용 순서에 의한 영 semi-naive 처리방법을 제안한다. 제안하는 처리방법은 새로운 semi-naive 알고리즘과 실행 시점에 다음에 적용할 규칙을 선택하는 선택전략들로 구성된다. 새로운 semi-naive 알고리즘은 동적 순서로 규칙을 적용하더라도 동일한 계산의 중복이 없고, 새로이 생성된 튜플을 다음의 규칙 적용에서 바로 이용할 수 있다. 본 논문에서는 순환질의 처리에 필요한 전체 규칙의 적용 횟수와 결합연산의 수가 최소가 될 수 있도록 다음에 적용할 규칙을 선택하는 세 가지 선택전략을 개발하였다. 실험적 비교를 통하여 제안하는 동적 규칙 적용 순서에 의한 semi-naive 처리방법이 기존의 순환 처리 방법에 비하여 전체 규칙 적용 횟수와 결합연산 횟수의 측면에서 뛰어난 성능을 보임을 실증하였다. In this paper, we propose a new fixed point evaluation technique for recursions, which is based on the dynamic rule-application order. In the proposed technique (or simply DYN), the next rule to be applied is determined at run time dynamically. DYN consists of a semi-naive algorithm and a set of selection strategies. The semi-naive algorithm allows dynamic ordering of rule applications and makes tuples generated by a rule application immediately available in the subsequent rule applications. After each rule application, the selection strategies determine the next rule by considering the syntactic structure of recursion and some information about the intermediate result up to the present. We develop these selection strategies so that the total number of rule applications and joins can be reduced. Through experimental comparisons, we show that DYN outperforms the previous evaluation techniques in terms of the total number of rule applications and joins.

산업용 음성 DB를 위한 XML 기반 메타데이터

주영희,홍기형,Joo Young-Hee,Hong Ki-Hyung 대한음성학회 2005 말소리 Vol.55 No.-

In this paper, we propose an XML based meta-data specification for industrial speech databases. Building speech databases is very time-consuming and expensive. Recently, by the government supports, huge amount of speech corpus has been collected as speech databases. However, the formats and meta-data for speech databases are different depending on the constructing institutions. In order to advance the reusability and portability of speech databases, a standard representation scheme should be adopted by all speech database construction institutions. ETRI proposed a XML based annotation scheme [51 for speech databases, but the scheme has too simple and flat modeling structure, and may cause duplicated information. In order to overcome such disadvantages in this previous scheme, we first define the speech database more formally and then identify object appearing in speech databases. We then design the data model for speech databases in an object-oriented way. Based on the designed data model, we develop the meta-data specification for industrial speech databases.

TV 가이드 영역에서의 음성기반 멀티모달 사용 유형 분석

김지영,이경님,홍기형,Kim Ji-Young,Lee Kyong-Nim,Hong Ki-Hyung 대한음성학회 2006 말소리 Vol.58 No.-

The development of efficient multimodal interfaces and fusion algorithms requires knowledge of usage patterns that show how people use multiple modalities. We analyzed multimodal usage patterns for TV-guide application scenarios (or tasks). In order to collect usage patterns, we implemented a multimodal usage pattern collection system having two input modalities: speech and touch-gesture. Fifty-four subjects participated in our study. Analysis of the collected usage patterns shows a positive correlation between the task type and multimodal usage patterns. In addition, we analyzed the timing between speech-utterances and their corresponding touch-gestures that shows the touch-gesture occurring time interval relative to the duration of speech utterance. We believe that, for developing efficient multimodal fusion algorithms on an application, the multimodal usage pattern analysis for the given application, similar to our work for TV guide application, have to be done in advance.