본 연구는 치매노인환자의 생활의 질을 향상시키기 위한 대화시스템의 개발에 목표를 둔다. 제안된 시스템은 주로 세 가지 모듈, 즉, 음성인식, 시간테이블에 의해 구분된 대화 데이터베이스의 자동검색, 그리고 간호사의 녹음음성으로 이루어진 맞장구 등의 긍정적인 대답, 등으로 구성되어 있다. 첫 단계로서, 치매환자가 간호시설에서 자주 발화하는 대화의 내용을 조사하였다. 다음으로, 환자들의 요구를 충족시키기 위해 그들의 발화 음성을 자동인식 하도록 구성하였다. 여기서 시스템의 응답은 전문 간호사의 녹음음성으로 설계되었다. 시스템의 평가를 위해서 시스템이 도입되었을 때와 되지 않았을 때의 비교연구를 실시하였고, 치료 전문가(occupational therapist)들이 비디오 촬영을 통해서 남성 대상자의 반응을 평가하였다. 평가 견과는 치매환자의 요구를 충족시키는데 있어서 대화 시스템이 전문간호사들보다 더욱 답적이었다는 것을 보여준다. 게다가 제안된 시스템은 상호 대화에 있어서 간호사들보다 환자가 더 많이 말하도록 유도함을 알 수 있었다.
본 연구는 치매노인환자의 생활의 질을 향상시키기 위한 대화시스템의 개발에 목표를 둔다. 제안된 시스템은 주로 세 가지 모듈, 즉, 음성인식, 시간테이블에 의해 구분된 대화 데이터베이스의 자동검색, 그리고 간호사의 녹음음성으로 이루어진 맞장구 등의 긍정적인 대답, 등으로 구성되어 있다. 첫 단계로서, 치매환자가 간호시설에서 자주 발화하는 대화의 내용을 조사하였다. 다음으로, 환자들의 요구를 충족시키기 위해 그들의 발화 음성을 자동인식 하도록 구성하였다. 여기서 시스템의 응답은 전문 간호사의 녹음음성으로 설계되었다. 시스템의 평가를 위해서 시스템이 도입되었을 때와 되지 않았을 때의 비교연구를 실시하였고, 치료 전문가(occupational therapist)들이 비디오 촬영을 통해서 남성 대상자의 반응을 평가하였다. 평가 견과는 치매환자의 요구를 충족시키는데 있어서 대화 시스템이 전문간호사들보다 더욱 답적이었다는 것을 보여준다. 게다가 제안된 시스템은 상호 대화에 있어서 간호사들보다 환자가 더 많이 말하도록 유도함을 알 수 있었다.
This study aims at developing dialog system to improve the quality of life of the elderly with a dementia. The proposed system mainly consists of three modules including speech recognition, automatic search of the time-sorted dialog database, and agreeable responses with the recorded voices of careg...
This study aims at developing dialog system to improve the quality of life of the elderly with a dementia. The proposed system mainly consists of three modules including speech recognition, automatic search of the time-sorted dialog database, and agreeable responses with the recorded voices of caregivers. For the first step, the dialog that dementia patients often utter at a nursing home is first investigated. Next, the system is organized to recognize the utterances in order to meet their requests or demands. The system is then responded with recorded voices of professional caregivers. For evaluation of the system, the comparison study was carried out when the system was introduced or not, respectively. The occupational therapists then evaluated a male subjects reaction to the system by photographing his behaviors. The evaluation results showed that the dialog system was more responsive in catering to the needs of dementia patient than professional caregivers. Moreover, the proposed system led the patient to talk more than caregivers did in mutual communication.
This study aims at developing dialog system to improve the quality of life of the elderly with a dementia. The proposed system mainly consists of three modules including speech recognition, automatic search of the time-sorted dialog database, and agreeable responses with the recorded voices of caregivers. For the first step, the dialog that dementia patients often utter at a nursing home is first investigated. Next, the system is organized to recognize the utterances in order to meet their requests or demands. The system is then responded with recorded voices of professional caregivers. For evaluation of the system, the comparison study was carried out when the system was introduced or not, respectively. The occupational therapists then evaluated a male subjects reaction to the system by photographing his behaviors. The evaluation results showed that the dialog system was more responsive in catering to the needs of dementia patient than professional caregivers. Moreover, the proposed system led the patient to talk more than caregivers did in mutual communication.
* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.
문제 정의
This study aims to improve the QOL of the elderly with a dementia[l,2,3]. The dementia possesses unique features that make nursing particularly burdensome.
Namely, family caregivers experience mental stress, burden, and depression as outcomes of nursing activities. Therefore, this study also aims to improve the QOL of family caregivers by lightening their nursing loads to some degree in long-term care[4,5].
제안 방법
However, its high performance is not always guaranteed owing to the ambient noisy environments and slurred speech of the elderly with dementia. In this study, therefore, the additional functions, such as an automatic search of database classified by a timetable of nursing home or chiming with user, supplement a shortcoming of speech recognition for maintaining natural interaction. Therefore, this enables system to promote natural conversation between system and user, even when system fails in recognizing speech of user correctly, or when the incoming speech is not registered in candidate lists.
In general, the elderly with dementia often finds it hard to remember the meaning of words used in their daily lives, or to think of words they want to say. In this study, therefore, we selected the most relevant dialogs as to how to talk to dementia patient for a virtual communication between patient and system, according to the following criteria on the basis of the experiences of professional caregivers or occupational therapists.
subject. The experiments were investigated for 90 minutes of each day during 5 days.
The comparative study was examined where one of the evaluations was performed with dialog system for 90 minutes of each day during 5 days. In this case, the interruption of caregivers was restricted during the experiment.
대상 데이터
For this study, the official approvals from the ethics committee of nursing facility as well as from family members of subject were first obtained in advance. The subject was 72 years old male patient with a vascular dementia. He has received the day-care service at nursing home from 8:30 a.
성능/효과
In evaluation results, we could find that the accuracies of speech recognition were degraded owing to subjects slurred voices mixed with regional dialects as well as his characteristic accents. Nevertheless, the supplementary functions, such as chiming with user by making agreeable responses, keep conversation smooth, so that he might regard system as a good listener.
후속연구
The present study aims to improve the QOL of the elderly who have been suffered from dementia. For realizing this purpose, we have developed dialog system to respond with a natural dialog to their needs.
참고문헌 (10)
Tomoeda CK. Bayles KA. Trosset MW. Azuma T. Mcgeagh A., Cross-Sectional Analysis of Alzheimer Disease Effects on Oral Discourse in a Picture Description Task, Alzheimer Disease & Associated Disorders. 10(4): 204-215, 1996
Minthon L. Edvinsson L. Gustafson L., Correlation Between Clinical Characteristics and Cerebrospinal Fluid Neuropeptide Y Levels in Dementia of the Alzheimer Type and Frontotemporal Dementia, Alzheimer Disease & Associated Disorders. 10(4): 197- 203, 1996
S. Nakagawa, A. Kai, T. Itoh and S. Kogure, 'Speech recognition and understanding of spoken dialogue', Proc. Int. Symposium on Spoken Dialogue, pp.5-1-5-6, 2000
H.Fujisaki, K.Shirai, S.Doshita, S.Nakagawa, etl., 'Overview of an intelligent system for information retrieval based on human-machine dialogue through spoken language', Proc. Int. Conf. Spoken Language Processing, pp.1-70- 73, 2000
Rainer Stiefelhagen, Jie Yang, Alex Waibel, Tracking Focus of Attention for Human- Robot Communication, IEEE-RAS International Conference on Humanoid Robots - Humanoids 2001, 22-24, 2001
A. Stolcke, K. Ries, N. Coccaro, E. Shriberg, etl., Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech, Computational Linguistics 26(3), 339- 373, 2000
H. Asoh, T. Matsui, J. Fry, F. Asano, and S. Hayamizu, A spoken dialog system for a mobile office robot, Proc. of Eurospeech'99, pp.1139-1142, Budapest, September, 1999
이 논문을 인용한 문헌
활용도 분석정보
상세보기
다운로드
내보내기
활용도 Top5 논문
해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다. 더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.