• Journal of Computing Science and Engineering
• /
• v.4 no.1
• /
• pp.1-22
• /
• 2010

A field of spoken dialog systems is a rapidly growing research area because the performance improvement of speech technologies motivates the possibility of building systems that a human can easily operate in order to access useful information via spoken languages. Among the components in a spoken dialog system, the dialog management plays major roles such as discourse analysis, database access, error handling, and system action prediction. This survey covers design issues and recent approaches to the dialog management techniques for modeling the dialogs. We also explain the user simulation techniques for automatic evaluation of spoken dialog systems.

• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.181-184
• /
• 2012

본 논문에서는 한국전자통신연구원 언어처리연구팀에서 개발하고 있는 차량용 대화 시스템을 위한 Dialog Act 태깅 코퍼스 구축 방법에 대해 기술하는 것을 목표로 한다. 차량용 태깅 코퍼스 구축 방법은 크게 차량용 대화 코퍼스 수집과 수집된 대화 코퍼스에 Dialog Act를 반자동으로 태깅하는 방법으로 나눌 수 있다. 차량용 대화 코퍼스 수집은 1) 대화플랜 맵 구축, 2) 표준대화 구축, 3) 자유대화 구축, 4) 사용자 발화에 패러프래징 발화 구축의 순으로 구축되었다. Dialog Act 태깅은 수집된 대화코퍼스로부터 슬롯 후보를 추출하여 슬롯 체계를 구축한 후 반자동 슬롯 태깅을 실시하고, 슬롯 태깅 결과와 Dialog Act Type을 조합하여 Dialog Act 태깅 코퍼스를 구축하였다. 이렇게 구축된 Dialog Act 태깅 코퍼스는 차량 공조시스템(에어컨, 히터 등) 및 차량 응급 조치 정보 서비스와 같은 차량용 대화 시스템에 적용 중에 있다.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.599-612
• /
• 2022

This study focuses on improving a word embedding model to enhance the performance of downstream tasks, such as those of dialog systems. To improve traditional word embedding models, such as skip-gram, it is critical to refine the word features and expand the context model. In this paper, we approach the word model from the perspective of subword embedding and attempt to extend the context model by integrating various sentence models. Our proposed sentence model is a subword-based skip-thought model that integrates self-attention and relative position encoding techniques. We also propose a clustering-based dialog model for downstream task verification and evaluate its relationship with the sentence-model-based subword embedding technique. The proposed subword embedding method produces better results than previous methods in evaluating word and sentence similarity. In addition, the downstream task verification, a clustering-based dialog system, demonstrates an improvement of up to 4.86% over the results of FastText in previous research.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.89-92
• /
• 2004

전화 음성용 화자인증 시스템 전화기에서 의뢰인의 ID와 음성을 입력받은 후 인증관련 처리론 PC에서 수행하여 그 인증 결과를 의뢰인의 전화로 알려주는 시스템으로 본 논문에서는 CTI(Computer Telephony Integration) 기술이 적용된 Dialog/4 보드를 이용하여 시스템을 구현하였다. Dialog/4 보드를 통하여 시스템에 입력된 ID와 음성에 대하여 신호처리와 특징 추출을 거친후 ID에 해당하는 화자모델과 배경화자 정보를 이용하여 유사도를 계산하여 의뢰인에 대한 인증 또는 거절의 결과를 알려준다. 실제의 전화음성을 이용한 화자인증 시스템이 성능평가에서 전화음성으로 실험을 할 경우 $99.6\%$의 인증률을 보여주었다.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4E
• /
• pp.170-177
• /
• 2002

The goal of the present research is to improve a quality of life of the elderly with a dementia. In this paper, it is realized by developing the dialog system that is controlled by three kinds of modules such as speech recognition engine, graphical agent, or database classified by a nursing schedule. The system was evaluated in an actual environment of a nursing facility by introducing it to an older male patient with dementia. The comparison study between dialog system and professional caregivers was then carried out at nursing home for 5 days in each case. The evaluation results showed that the dialog system was more responsive in catering to needs of dementia patient than professional caregivers. Moreover, the proposed system led the patient to talk more than caregivers did.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.170-170
• /
• 2002

The goal of the present research is to improve a quality of life of the elderly with a dementia. In this paper, it is realized by developing the dialog system that is controlled by three kinds of modules such as speech recognition engine, graphical agent, or database classified by a nursing schedule. The system was evaluated in an actual environment of a nursing facility by introducing it to an older male patient with dementia. The comparison study between dialog system and professional caregivers was then carried out at nursing home for 5 days in each case. The evaluation results showed that the dialog system was more responsive in catering to needs of dementia patient than professional caregivers. Moreover, the proposed system led the patient to talk more than caregivers did.

• Fashion & Textile Research Journal
• /
• v.17 no.4
• /
• pp.541-549
• /
• 2015

Korean traditional mask play was done at outdoor to let spectators join the play and take mask at performance and to have disadvantage of poor transfer of dialog to the spectators. Performers transferred dialog directly and/or indirectly by using visual costume, and Tongyeong Ogwangdae with many dialogue expressions concerning the costume made use of proper intention to help spectators understand. In this study, the author watched performance of Tongyeong Ogwangdae to collect and investigate not only image material but also photograph material and to classify intention of the costume into three: First, contents of the dialog were intended to make shape. The costumes of Hongbaek Yangban, Meoktal Yangban and Jorijung of the 2nd section gave spectators contents of the play, and the costume of Halmi Yangban of Nochangtal of the 4th section described dialog of Halmi. Second, dialog had connotative metaphor. The costume of Yeongno of Yeongnotal of the 3rd section symbolized an unfinished dragon, while that of Halmi of Nongchangtal of the 4th section did sacred of Halmi. And, Nongchagtal Ai's costume of the 4th section prayed for value of Ai, richness of the life and fecundity. Third, conflict between characters was intended by indirect media. The costume of Maltukee of metaphor mask of the 2nd section became base of the assertion supporting that Maltukee had better birth history than Yangban had, and the costume of Yeongnoyangban of Yeongnotal of the 3rd section produced conflict at disclosure of identity.

• Korean Journal of Social Welfare
• /
• v.60 no.4
• /
• pp.253-276
• /
• 2008

This study investigated dialog sequence prototype that was the structure of communication, which could be shown in family counseling conversation between therapists and clients. The study was intended to review the process stages of family counseling through literature review, and divided functional phases into 'atmosphere formation phase', 'family evaluation phase', 'persuasion phase of cognitive change', 'confirmation phase of change experience', and 'termination phase'. The study selected two family therapists and 30 clients for research objects. They allowed data collections for the study after the explanation about the research objects. The transcribers were trained by the consent of transcription, which used particular symbol for verbal and nonverbal contents in conversation. The transcribed data were analyzed by dialog grammar, one of the linguistic dialog analysis method developed by Hundsnurscher(1994). This study described and explained dialog sequence prototype that displayed in conversation between family therapist and client through the total sessions in family therapy. The study found three types of dialog sequence prototype in 'atmosphere formation phase', eight types in 'family evaluation phase', nine types in 'persuasion phase of cognitive change', eight types in 'confirmation phase of change experience', and eight types of 'termination phase'. Even if the dialog sequence prototype mentioned above cannot be applied to the process of family therapy at its face value, these findings may contribute to beginners in counseling and graduate students majoring family therapy to do practice in counseling. The research has a limitation in which the study investigated dialog sequence prototype of conversation in two persons. Future research needs to include dialog sequence prototype of conversation among more than three persons. Specifically, when a family therapist do family counseling, he/she treats more than three family members as usual. Therefore, the researchers hope that future study investigates dialog sequence prototype between therapist and client, client and client, among therapist, client and other family members.

• Journal of Convergence for Information Technology
• /
• v.9 no.8
• /
• pp.1-8
• /
• 2019

Dialog system is becoming a new dominant interaction way between human and computer. It allows people to be provided with various services through natural language. The dialog system has a common structure of a pipeline consisting of several modules (e.g., speech recognition, natural language understanding, and dialog management). In this paper, we tackle a task of domain classification for the natural language understanding module by employing machine learning models such as convolutional neural network and random forest. For our dataset of seven service domains, we showed that the random forest model achieved the best performance (F1 score 0.97). As a future work, we will keep finding a better approach for domain classification by investigating other machine learning models.

• Journal of Convergence for Information Technology
• /
• v.9 no.9
• /
• pp.1-12
• /
• 2019

A dialog system becomes a new way of communication between human and computer. The dialog system takes human voice as an input, and gives a proper response in voice or perform an action. Although there are several well-known products of dialog system (e.g., Amazon Echo, Naver Wave), they commonly suffer from a problem of out-of-domain utterances. If it poorly detects out-of-domain utterances, then it will significantly harm the user satisfactory. There have been some studies aimed at solving this problem, but it is still necessary to study about this intensively. In this paper, we give an overview of the previous studies of out-of-domain detection in terms of three point of view: dataset, feature, and method. As there were relatively smaller studies of this topic due to the lack of datasets, we believe that the most important next research step is to construct and share a large dataset for dialog system, and thereafter try state-of-the-art techniques upon the dataset.