• 말소리와 음성과학
• /
• 제3권3호
• /
• pp.19-26
• /
• 2011

Previous laboratory studies have shown that prosodic structures are encoded in the modulations of phonetic patterns of speech including suprasegmental as well as segmental features. Drawing on a prosodically annotated large-scale speech data from the Buckeye corpus of conversational speech of American English, the current study first evaluated the reliability of prosody annotation by a large number of ordinary listeners and later examined whether and how prosodic prominence influences the phonetic realization of multiple acoustic parameters in everyday conversational speech. The results showed that all the measures of acoustic parameters including pitch, loudness, duration, and spectral balance are increased when heard as prominent. These findings suggest that prosodic prominence enhances the phonetic characteristics of the acoustic parameters. The results also showed that the degree of phonetic enhancement vary depending on the types of the acoustic parameters. With respect to the formant structure, the findings from the present study more consistently support Sonority Expansion Hypothesis than Hyperarticulation Hypothesis, showing that the lexically stressed vowels are hyperarticulated only when hyperarticulation does not interfere with sonority expansion. Taken all into account, the present study showed that prosodic prominence modulates the phonetic realization of the acoustic parameters to the direction of the phonetic strengthening in everyday conversational speech and ordinary listeners are attentive to such phonetic variation associated with prosody in speech perception. However, the present study also showed that in everyday conversational speech there is no single dominant acoustic measure signaling prosodic prominence and listeners must attend to such small acoustic variation or integrate acoustic information from multiple acoustic parameters in prosody perception.

• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.702-736
• /
• 2023

Artificial Intelligence (AI) and the technologies powered by AI fuel the fourth industrial revolution. Being the primary adopter of such innovations, banking has recently started using the most common AI-based technology, i.e., conversational agents. Although research extensively focuses on this niche area and provides bibliometric understanding for such agents in other industries, a similar review with scientometric insights of the banking literature concerning AI conversational agents is absent till date. Furthermore, in the era following the pandemic, banks are faced with the imperative to provide solutions that align with the changing landscape of remote consumer behavior. As a result, banks are proactively integrating technology-driven solutions, such as automated agents, to effectively address the growing demand for remote customer support. Hence more research is needed to perfect such agents. In order to bridge these existing gaps, the present study undertook a comprehensive examination of two decades' worth of banking literature. A meticulous review was conducted, analyzing approximately 116 papers published from 2003 to 2023. The aim was to provide a scientometric overview of the topic, catering to the research needs of both academic and industrial professionals. Holistically, the study seeks to present a macro-view about the existing trends in AI based banking conversational agents' literature while focusing on quantity, qualitative and structural indicators that are effectively necessary to offer new directions for the AI-based banking solutions. Our study, therefore, presents insights surrounding the literature, using selected techniques related to performance analysis and science mapping.

• 대한전자공학회논문지
• /
• 제9권1호
• /
• pp.7-16
• /
• 1972

주음결합효과의 영향을 받은 음성시료를 스펙트럼 애나라이저로 주파수를 분석하여 분석하여 연속음성은 단순한 단음이 연속된 집합체가 아님을 알았으며 한글 연속음의 Formant 주파수영역을 결정해 냈다.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 1996년도 추계학술대회 논문
• /
• pp.15-21
• /
• 1996

This paper describes a development of conversational program for lathe. The proposed program is a NC programming system specialized for use in machine tool controls. Its easy to use graphic interface built-in database capabilities make it an ideal way to program part on the shop floor. In order to manage effectively machining process it proposed the algorithm of tree structures for design processing. Also using interative structure it proposed the methods of conversational programming to generate automatically NC program.

• 복식문화연구
• /
• 제18권6호
• /
• pp.1179-1193
• /
• 2010

For a good design, it is important to understand consumers and trend of textile and fashion design. Previous researches on textile pattern design with CAD have been done. They have studied on Korean traditional floral motives/hand painting or some geometric patterns. Few studies have been done on conversational design. Therefore the purpose of study was to observe types of textile pattern design for the recent fiver years and determine fabric pattern trends, especially on the conversational motifs. The types of patterns were analysed with professional panels from the 2005～2009 collection sources, using SPSS program. This study was also develop textile patterns creating using CAD. We conducted design process on motif creating, repeat, and mapping jobs, using textile special design program Prima vision and Photoshop CS3.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 춘계 학술대회 발표논문집
• /
• pp.101-104
• /
• 2006

The present study examined two acoustic characteristics(duration and intensity) of vowels produced by 4 cerebral palsic adults and 4 nondisabled adults in conversational and clear speech. In this study, clear speech means: (1) slow one's speech rate just a little, (2) articulate all phonemes accurately and increase vocal volume. Speech material included 10 bisyllabic real words in the frame sentences. Temporal-acoustic analysis showed that vowels produced by two speaker groups in clear speech(in this case, more accurate and louder speech) were significantly longer than vowels in conversational speech. In addition, intensity of vowels produced by cerebral palsic speakers in clear speech(in this case, more accurate and louder speech) was higher than in conversational speech.

• International journal of advanced smart convergence
• /
• 제12권3호
• /
• pp.186-191
• /
• 2023

This study would investigate the generative AIs currently in service in the era of hyperscale AIs and explore measures for the use of generative AIs, focusing on 'ChatGPT,' which has received attention as a leader of generative AIs. Among the various generative AIs, this study selected ChatGPT, which has rich application cases to conduct research, investigation, and use. This study investigated the concept, learning principle, and features of ChatGPT, identified the algorithm of conversational AI as one of the specific cases and checked how it is used. In addition, by comparing various cases of the application of conversational AIs such as Google's Bard and MS's NewBing, this study sought efficient ways to utilize them through the collected cases and conducted research on the limitations of conversational AI and precautions for its use. If connected to city-related databases, it can provide information on city infrastructure, transportation systems, and public services, so residents can easily get the information they need. We want to apply this research to enrich the lives of our citizens.

• Journal of Information Technology Applications and Management
• /
• 제30권4호
• /
• pp.11-28
• /
• 2023

This paper proposes a method of integrating ChatGPT with traditional chatbot systems to enhance conversational artificial intelligence(AI) and create more efficient conversational systems. Traditional chatbot systems are primarily based on classification models and are limited to intent classification and simple response generation. In contrast, ChatGPT is a state-of-the-art AI technology for natural language generation, which can generate more natural and fluent conversations. In this paper, we analyze the business service areas that can be integrated with ChatGPT and traditional chatbots, and present methods for conducting conversational scenarios through case studies of service types. Additionally, we suggest ways to integrate ChatGPT with traditional chatbot systems for intent recognition, conversation flow control, and response generation. We provide a practical implementation example of how to integrate ChatGPT with traditional chatbots, making it easier to understand and build integration methods and actively utilize ChatGPT with existing chatbots.

• 정보처리학회논문지B
• /
• 제11B권1호
• /
• pp.91-98
• /
• 2004

본 논문에서는 온라인 대화 행위에서 다양한 미디어를 지원하기 위하여 XML(eXtensible Markup Language)을 이용하는 방법을 제안한다. 제안한 방법은 온라인 대화 행위에서 미디어 정보를 XML 기반 메시지로 변환하여 기존 텍스트 기반 메시지와 유사하게 처리한다. 이때 XML 기반 메시지와 미디어는 서버에 저장되며, XML 기반 메시지는 하나의 XML 문서로 통합된 후 XSLT 문서를 적용하여 HTML 문서를 생성한다. 각 클라이언트의 대화자는 HTML 문서의 하이퍼링크를 이용하여 미디어를 재생 및 프레젠테이션 한다. 제안한 방법은 온라인 대화 행위에서 텍스트, 이미지, 오디오, 비디오 등의 다양한 미디어의 사용을 효율적으로 지원하고, 또한 XML 태그의 확장 및 변경에 따라 텍스트 기반 메시지의 글자 크기, 색깔, 스타일 등의 유지보수에 효율적이다. 적용 예로서, 온라인 대화 행위에서 미디어를 지원하기 위하여 클라이언트-서버구조를 가지는 시스템을 구현하였으며, 각 대화자는 웹 브라우저에서 JAVA 애플릿과 서블릿을 사용하여 텍스트 및 미디어 기반 메시지를 입력하며, 대화자가 메시지를 입력할 때마다 대화 메시지가 자동으로 갱신되도록 하였다. 대화자는 사용자 인터페이스상의 대화 메시지에서 하이퍼링크의 클릭으로 미디어를 재생 및 프레젠테이션 한다. 제안한 방법의 응용 분야로는 원격 교육, 게임, 협업 등이다.

• 디자인학연구
• /
• 제16권1호
• /
• pp.117-126
• /
• 2003

인간과 컴퓨터의 상호작용은 컴퓨터의 기술적 발달과 함께 다양하게 변화하여 왔으며 웹의 보편화와 함께 웹의 특성을 반영한 다양한 형식과 방법의 상호작용이 시도되고 있다. 이러한 다양한 상호작용의 개념중 대화형 에이전트는 대화의 대상으로 캐릭터를 사용하며 대화에 의한 상호작용을 통해 자연스럽고 인간적이며 직관적인 상호작용을 제시하고 있다. 그러나 현재까지의 연구는 그 구현을 중심으로 진행되고 있으며 웹에서의 실질적인 적용은 시험적 단계를 거치고 있다. 따라서 본 연구에서는 가상 강좌 사이트에서 보다 적극적인 활용대상으로서 대화형 에이전트를 적용하기 위해 대화형 에이전트의 상호작용 방식의 주요 개념인 대화에 대하여 고찰하였다. 다음으로 웹에서 이루어지는 대화적 특성을 연구하고 웹에서의 대화 구성 방식을 도출하였다. 이를 바탕으로 대화형 에이전트를 구현하여 가상 강좌 사이트에 적용하였으며 사이트 운영 및 평가를 통해 대화형 에이전트의 적용 가능성을 살펴보았다.