• 대한기관식도과학회지
• /
• 제7권2호
• /
• pp.161-167
• /
• 2001

Background and Objectives： Total laryngectomy is often required for advanced cases. But this operation induced the many inconvenience of basic daily life. Early diagnosis of laryngeal cancer is very important to prevent from this disastrous condition. In this point of view, mass screening test for early detection of laryngeal cancer is necessary. Screening test using voice has many advantages such as simple, less interventional. Voice collection by Automatic Response System(ARS) is comfortable and easy to got acoustic sample. Thus author tried to got the acoustic parameters which can differentiate normal, benign. and malignant laryngeal diseases and also checked the availability of parameters on neural network system. Materials and Methods: Author has evaluated the voice from 17 laryngeal cancer patients and 45 benign laryngeal disease patients who visited at Department of Otolaryngology, Pusan National University Hospital from May 1998 to April 2001, and 15 normal control. Author chose the sir Parameters (Jitt. vFo, Shim, vAm, NHR, SPI) that was thought to be related with voice collected by ARS among thirty-three parameters analysed by a Multi-Dimensional Voice Program (MDVP). Two-step neural network was used for the availability of six parameters. Results: The detection rate of normal voice by ARS voice analysis is 78.5% and detection rate of abnormal voice was 97.1 o/o. Among abnormal voice, the detection rate of benign laryngeal diseases and laryngeal cancers were 82.4 o/o, 70.6% respectively. Conclusion: Author concluded that six parameters and Matlab based neural network software may be effective in development of acoustic screening system for laryngeal cancer and further study should be necessary for development of new acoustic parameters.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권3호
• /
• pp.59-63
• /
• 2019

VoIP technology is a technology for exchanging voice or video data through IP network. Various protocols are used for this technique, in particular, RTP(Real-time Transport Protocol) protocol is used to exchange voice data. In recent years, with the development of communication technology, there has been an increasing tendency of services such as "Kakao Voice Talk" to exchange voice and video data through IP network. Most of these services provide a service with security guarantee by a user authentication process and an encryption process. However, RTP protocol does not require encryption when transmitting data. Therefore, there is an exposition risk in the voice data using RTP protocol. We will present the risk of the situation where packets are sniffed in VoIP(Voice over IP) communication using RTP protocol. To this end, we configured a VoIP telephone network, applied our own sniffing tool, and analyzed the sniffed packets to show the risk that users' data could be exposed unprotected.

• 한국정보통신학회논문지
• /
• 제7권4호
• /
• pp.678-683
• /
• 2003

본 연구에서는 컴퓨터 통신망에서 음성/데이터 통합을 위하여 이행단계별 성능평가를 실시하고 최적의 모델을 제안하였다. 먼저 기존에 있는 PBX를 데이터 네트워크에서 수용할 경우3.3ms에서 3.5ms 지연이 발생하였고, IP를 이용한 음성/데이터 네트워크 통합시 0.7ms에서 0.9ms지연이 발생하였다. IP+/ATM를 이용한 음성/데이터 네트워크에서는 0.26ms에서 0.32ms 지연이 발생하였고, 일부 지역 네트워크에 장애를 발생 할 경우 IGRP 라우팅 프로토콜은 1.1ms-1.3ms, OSPF 라우팅 프로토콜은 0.9ms-1.2ms의 지연이 발생하였다. 본 연구에서는 컴퓨터 통신망에서 음성/데이터 통합을 하기 위해서는 음성/데이터 통합망은 IP+ATM를 이용하고, 계층적인 통신망에서 사용하는 라우팅 프로토콜은 OSPF를 사용할 때 최적의 성능을 보장 받을 수 있음을 확인하였다.

• 한국통신학회논문지
• /
• 제35권3B호
• /
• pp.398-407
• /
• 2010

다양한 트래픽에 대한 사용자의 요구 증대와 망 기술의 발전은 각각의 분리된 망을 하나의 망으로 융합해가고 있다. 하지만 융합 망에서 음성 사용자에게 QoE를 제공하기 위해서는 융합 망에서 VoIP 성능분석 연구가 필요하다. 그러므로 본 논문에서는 사용자가 융합 망에서 VoIP를 사용할 때 발생할 수 있는 음성 품질저하 시나리오를 제시한다. 특히, 본 논문에서는 융합 망 구성요소 별로 시나리오를 나타내고 음성 품질 개선 포인트를 찾는다. 시뮬레이션 결과, HSDPA 무선 계층에서 패킷 손실이 발생했을 경우와 3GPP와 인터넷 프로토콜 백본의 게이트웨이인 GGSN에서 QoS 파라미터 mapping을 하지 않았을 경우, 그리고 무선 랜에서 non-QoS AP를 사용하였을 경우에 음성 품질저하가 발생하는 것을 살펴 볼 수 있었다.

• 한국통신학회논문지
• /
• 제28권8B호
• /
• pp.683-690
• /
• 2003

In this paper we present a theoretical framework for the network design with delay QoS guarantee to a voice at the packet level. Especially, we propose a method for estimating the bandwidth at the ingress edge routers accommodating the voice connections and data sessions in the next-generation If network. First, we describe network architecture for VoIP (Voice over IP) services in the NGN (Next Generation Network). After that, we propose a procedure for dimensioning the bandwidth at the output port of a router that accommodates voice and data traffic using the non-preemptive queuing system with strict priority service scheme. Via numerical experiments we illustrate the implication of the proposition.

• 대한임베디드공학회논문지
• /
• 제2권2호
• /
• pp.82-94
• /
• 2007

Wireless sensor networking technology is one of the basic infrastructures for ubiquitous environment. It enables us to gather various sensory data such as temperature, humidity, gas leakage, and speed from the remote sensor devices. To support these networking functions, IEEE WPAN working group makes standards for PHY and MAC, while ZigBee Alliance defines the standards for the network, security, and applications. The low-rate WPAN was emerged to have the characteristics of network resilience, low cost, and low power consumption. It has a broad range of applications including, but not limit to industrial control and monitoring, home automation, disaster forecast and monitoring, health care. In order to provide more intelligent and robust services, users want voice-based solutions to accommodate to low-rate WPAN. In this paper, we have evaluated voice quality of an IEEE 802.15.4 standard compliant voice node. Specifically, it includes the design of a voice node and experiments based on the prediction of voice quality using the E-model suggested by ITU-T G.107, and the network communication mechanisms considering beacon-enabled and nonbeacon-enabled networks for real-time voice communications.

• 전기학회논문지
• /
• 제67권9호
• /
• pp.1210-1215
• /
• 2018

Recently, as the IoT(Internet of Things) and AI(Artificial Intelligence) technologies have developed, smart toys that can understand and act on the language of human beings are being studied. In this paper, we study voice learning using CNN(Convolutional Neural Network) by applying artificial intelligence based voice secretary technology to smart toy. When a human voice command gives, Smart Toy recognizes human voice, converts it into text, analyzes the morpheme, and conducts tagging and voice learning. As a result of test for the simulator program implemented using Python, no malfunction occurred in a single command. And satisfactory results were obtained within the selected simulation condition range.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.568-570
• /
• 2018

최근 이동통신기술의 급속한 발달과 보급으로 LTE(Long Term Evolution) 기술은 스마트폰 서비스를 넘어 산업통신이나 긴급통신을 비롯하여 다양한 분야로 확대되고 있다. 본 연구에서는 LTE 기술의 응용 분야로서 LTE-R을 기반으로 하는 철도통신의 서비스 분야 가운데 하나인 음성서비스의 전송성능을 분석하고자 한다. 본 연구에서는 LTE-R 네트워크의 응용서비스 관점에서 성능을 분석하여 응용서비스가 사용자 만족도에 미치는 영향을 살펴본다. 분석방법으로는 NS(Network Simulator)-3에 기반한 컴퓨터 시뮬레이션을 사용하며 분석대상 트래픽으로는 VoIP(Voice over Internet Protocol) 규격 음성트래픽을 사용한다. 본 연구의 결과는 LTE-R 네트워크 구축뿐 아니라 LTE-R 네트워크를 대상으로 하는 응용서비스 개발에 활용이 가능하다. 다음은 요약문 입니다.

• 한국통신학회논문지
• /
• 제39C권1호
• /
• pp.90-96
• /
• 2014

센서 네트워크를 위한 표준인 IEEE802.15.4는 저전력, 저속 데이터 통신이 특징으로 주로 ZigBee 네트워크와 같은 Wireless Personal Area Network (WPAN)를 구성하기 위해 사용하고 있다. 그러나 최근 센서 네트워크 기반의 음성통신과 Session Initiation Protocol (SIP)를 연동하여 장거리 및 대규모 사용자를 지원하기 위한 연구가 활발히 진행되고 있다. 본 논문에서는 센서 네트워크 기반의 음성통신과 SIP를 연동하여 다수 사용자 지원하고 기존 시스템을 하나의 통합 Base Station으로 설계하였다. 또한, 설계한 Base Station의 성능을 평가하기 위하여 사용자수 증가에 따른 Packet 수와 Delay를 측정하였다.

• 한국통신학회논문지
• /
• 제25권3B호
• /
• pp.423-430
• /
• 2000

Future microcellular systems will require distributed network control. A packet-switched network is suitable for this requirement. The packet reservation multiple access(PRMA) is a Reservation-ALOHA like protocol for wireless terminals to transmit packet speech to a base station. It allows spatially distributed users in cellular systems to transmit packeted voice and data to a common base station using a shared channel. In the existing PRMA, the problem is that the voice packets may collide with the data packets due to simultaneous channel access. the problem may be a major performance degradation factor to a voice and data mixed system. We propose a new PRMA method that integrates voice and data traffic efficiently by resolving the collision problem between data and voice packets. The proposed PRMA method gives a performance improvement than the existing PRAMA method in terms of voice packet dropping probability and data delay characteristic. From analytic results, we can confirm that the proposed PRMA method show a performance improvement than the existing PRMA protocol.