• 대한음성학회지:말소리
• /
• 제43호
• /
• pp.113-125
• /
• 2002

As there are needs to search the Web information via wire or wireless telephones, VoiceXML forum was established to develop and promote the Voice eXtensible Markup Language (VoiceXML). VoiceXML simplifies the creation of personalized interactive voice response services on the Web, and allows voice and phone access to information on Web sites, call center databases. Also, it can utilize the Web-based technologies, such as CGI(Common Gateway Interface) scripts. In this paper, we have developed the voice portal service platform based on VoiceXML called TeleGateway. It enables integration of voice services with data services using the Automatic Speech Recognition (ASR) and Text-To-Speech (TTS) engines. Also, we have showed the various services on voice portal services.

• 한국IT서비스학회지
• /
• 제20권5호
• /
• pp.189-207
• /
• 2021

Voice interaction combined with artificial intelligence is poised to revolutionize human-computer interactions with the advent of virtual assistants. This paper is analyzing interactive elements of AI-based voice recognition services such as sympathy, assurance, intimacy, and trust on intention to use. The questionnaire was carried out for 284 smartphone/smart TV users in Korea. The collected data was analyzed by structural equation model analysis and bootstrapping. The key results are as follows. First, AI-based voice recognition service characteristics such as sympathy, assurance, intimacy, and trust have positive effects on interactivity with the AI-based voice recognition service. Second, the interactivity with the AI-based voice recognition service has positive effects on intention to use. Third, AI-based voice recognition service characteristics such as interactional enjoyment and intimacy have directly positive effects on intention to use. Fourth, AI-based voice recognition service characteristics such as sympathy, assurance, intimacy and trust have indirectly positive effects on intention to use the AI-based voice recognition service by mediating the effect of the interactivity with the AI-based voice recognition service. It is meaningful to investigate factors affecting the interactivity and intention to use voice recognition assistants. It has practical and academic implications.

• 한국정보통신설비학회:학술대회논문집
• /
• 한국정보통신설비학회 2009년도 정보통신설비 학술대회
• /
• pp.99-103
• /
• 2009

Recently, as wired and wireless communication services have rapidly developed and multimodal mobile devices which have various characteristics have widely spread, the need for new convergence services increases. The growing population of VoIP technologies and the high communication expense yield that the market of IP based telephony such as WiFi phone and IP phone is substituted for one of the conventional PSTN telephony. With the help of this trend, the wireline network operators desire to find a market in mobile networks. Therefore, they focus on Fixed Mobile Convergence (FMC) service as one of the key factors to accomplish this goal. FMC services are able to provide the mobility of voice services between circuit switched and packet switched networks. IP Multimedia Subsystem (IMS) based Voice Call Continuity (VCC) is one of the schemes to embody FMC services. As Application Server (AS) which has this VCC function provides seamless handover of services between heterogeneous networks, FMC subscribers can communicate seamlessly with others m WiFi domain and COMA domain using WiFi-COMA dual phone. Most of enterprises have already introduced IP network infrastructure and IP-PBX (Private Branch eXchange) for telephony. However, the problems of high communication cost and work inefficiency due to frequent outside jobs or business trips have remained. In order to solve these problems, demands for enterprise FMC services increase. In this paper, we introduce a new IP-PBX based VCC model that can provide seamless handover of voice services between WiFi and COMA networks for enterprise users and we investigate some interworking and security issues between Soft Switch (SSW) and IMS, or between IMSs. In addition, we introduce a new service that can provide the continuity of voice sessions as well as video sessions using Multimedia Session Continuity (MMSC) technology which has evolved from VCC. This service is expected to be one of the next-generation personalized services based on user's context.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.387-390
• /
• 2004

In this paper, we design and implement practical application service using VoiceXML. And we suggest new solutions of problems can be occurred when implementing a new systems using VoiceXML, based on the fact. Up to now, speech related services were developed using API (Application Program Interface) and programming languages, which methods depend on system architectures. It thus appears that reuse of contents and resource was very difficult. To solve these problems, nowadays, companies develop their applications using VoiceXML. Advantages of using VoiceXML when developing services are as follows. First, we can use web developing technologies and technologies for transmitting web contents. And, we can save labors for low level programming like C language or Assembler language. And we can save labors for managing resources, too. As the result of these advantages, we can reduce developing hours of applications services and we can solve problem of compatibility between systems. But, there's poor grip of actual problems can be occurred when implementing their own services using VoiceXML. To overcome these problems, we implemented interactive stock trading system using VoiceXML and concentrated our effort to find out problems when using VoiceXML. And then, we proposed solutions to these problems and analyzed strong points and weak points of suggested system.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2004년도 춘계 학술대회 발표논문집
• /
• pp.125-130
• /
• 2004

In this paper, we explain telecommunication services based on spoken language information technology. There are three different kinds of services. The first is based on Advanced Intelligent services(AIN). We built a Intelligent Peripheral(IP)with speech recognition, speech synthesis and VoiceXML interpreter. The second is based on KT-HUVOIS, a proprietary speech platform based on VoiceXML. The third is based on VoiceXML interpreter. We explain various services depending on these platforms in detail.

• 디지털융복합연구
• /
• 제9권5호
• /
• pp.225-233
• /
• 2011

인터넷 전화는 IP 기반 인터넷에서 VoIP(Voice over IP) 기술을 이용해서 음성 전화를 지원하는 인터넷 서비스다. 인터넷 전화는 영상통화, 메시징과 같은 인터넷 멀티미디어 서비스를 융합한 음성전화 서비스를 지원할 수 있는 장점을 갖고 있다. 특히 스마트폰을 통한 인터넷 소셜 네트워크 서비스가 보급되면서 기존의 전화망을 대체하는 서비스로써 인터넷 전화에 대한 연구와 개발이 활발히 진행되고 있다. 본 논문에서는 SIP(Session Initiation Protocol) 기반 인터넷 전화의 음성 통화 내용을 녹취하는 시스템의 설계 및 구현에 대해 설명한다. 인터넷 전화 녹취 시스템은 리눅스 기반으로 양방향 음성 스트림을 믹싱하는 기능, 라이브 패킷 스니핑 기능, 녹취 음성 파일 송신 기능은 공개 소프트웨어를 사용해서 구현하였다. 향후 개발된 시스템은 VoIP 기반 콜센터 시스템 등과 같은 복합 시스템을 구축하는데 있어 기반 기술로 활용될 계획이다.

• 한국음향학회지
• /
• 제21권1호
• /
• pp.27-36
• /
• 2002

VoiceXML (Voice extensible Markup language)은 음성 대화를 웹의 마크업 언어로 기술할 수 있는 차세대 대화형 음성 서비스를 위한 표준이다. 현재 발표된 VoiceXML 1.0 사양은 음성대화의 기술에 초점을 두고 있으며, 음성 서비스의 시작 시점에 관해서는 언급이 없다. 본 논문에서는 사용자에 의해 시작하는 주문형 (on-demand) 음성 서비스 (inbound call) 뿐만 아니라, 최근에 고객관계관리 (CRM: Customer Relationship Management) 등에서 요구되는 시스템에 의한 푸쉬형 음성 서비스 (outbound call)가 가능한 VoiceXML 플랫폼을 설계하고 구현하였다. 또한, 본 논문에서는 W3C (World Wide Web Consortium)의 호 제어 요구사항 (Call Control Requirements)을 바탕으로 음성 대화 중에 팩스 송수신이 가능하도록 VoiceXML 문서형 정의 (UTD: Document Type Definition)를 확장하였다.

• 지능정보연구
• /
• 제28권2호
• /
• pp.279-306
• /
• 2022

공공기관과 정부는 시민에게 음성 기반 서비스 챗봇을 제공함으로써 시민 복지를증진하고 사회적 취약계층과 원활한 공공소통을 도모할 수 있다는 전제로 논의를 전개한다. 이 논문의 연구 목적은 지능형 정부가 ICT를 기반으로 조직 내외 지식 및 정보를 데이터화하고 체계화하여 능률적으로 관리하고 시민들, 특히 취약계층의 정보 접근과 활용을 용이하게 하여 신속하고 효율적인 행정서비스를 제공해 줄 방안을 제안하기 위함이다. 연구방법으로 소규모 설문조사를 통해 음성기반 서비스 제공을 앞둔 공공기관에 대한 시민들의 태도, 인식 및 기대가 긍정적임을 확인하고, 인공지능에 관한 지식을 갖춘 전문가들 인터뷰를 통해 음성기반 서비스에 필요한 기술적 측면과 공공기관 음성기반서비스 제공의 의의 및 필요성, 구축시 고려해야 할 제반사항들과 정책적 제언, 시사점을 살펴보고 한계 및 연구발전에 대해 고민해본다. 결과적으로, 챗봇의 음성기반서비스는 더 폭넓은 시민들이 지능형 정부에 참여를 실현하며, 정보 접근성을 강화하고 사회적 취약계층의 인권 및 기본권 보장·강화하는 사회적 배려와 디지털 포용을 실천하는 계기와 발판을 제공함에 큰 의의를 지닌다.

• 한국정보통신학회논문지
• /
• 제5권5호
• /
• pp.916-922
• /
• 2001

본 논문에서는 기지국과 단말기간의 전파지연이 비교적 짧은 마이크로셀 환경의 패킷 CDMA망에서 음성과 데이터를 통합 서비스하기 위한 MAC 프로토콜을 제안한다. 제안한 프로토콜을 위한 시스템의 상향링크 채널은 프레임들 구성하는 타임 슬롯과 각 슬롯별 확산코드에 의하여 제공된다. 지연에 민감한 음성 트래픽에 더 높은 우선순위를 부여하여, 음성 트래픽인 경우에는 발음구간 동안 임의의 확산코드를 예약하여 서비스된다. 반면, 데이터 트래픽은 매 패킷이 발생할 때마다 기지국으로부터 수신한 현재 슬롯의 예약 상태 정보를 기반으로 서비스된다. 성능분석의 결과, 본 논문에서 제안한 기법은 음성과 데이터 패킷간의 충돌이 전혀 발생하지 않으므로 주어진 패킷 누락률 범위 내에서 수용 가능한 최대 음성 단말기 수를 증가시킬 수 있었다.

• 한국통신학회논문지
• /
• 제25권12B호
• /
• pp.2109-2119
• /
• 2000

In this paper, the Packet CDMA Reservation ALOHA protocol is proposed to support the multi-traffic services such as voice and videophone services with handoff calls, high-rate data and low-rate data services efficiently on the multi-rate transmission in uplink cellular systems. The frame structure, composed of the access slot and the transmission slot, and the proposed access permission probability based on the estimated number of contending users for each service are presented to reduce MAI. The assured priority to the voice and the videophone handoff calls is given through higher access permission probability. And through the proposed code assignment scheme, the voice service can be provided without the voice packet dropping probability in the CDMA/PRMA protocols. The code reservation is allowed to the voice and the videophone services. The low-rate data service uses the available codes during the silent periods of voice calls and the remaining codes in the codes assigned to the voice service to utilize codes efficiently. The high-rate data service uses the assigned codes to the high-rate data service and the remaining codes in the codes assigned to the videophone service. Using the Markov-chain subsystem model for each service including the handoff calls in uplink cellular systems, the steady-state performances are simulated and analyzed. After a round of tests for the examples, through the proposed code assignment scheme and the access permission probability, the Packet CDMA Reservation ALOHA protocol can guarantee the priority and the constant QoS for the handoff calls even at large number of contending users. Also, the data services are integrated efficiently on the multi-rate transmission.