• 대한후두음성언어의학회지
• /
• 제24권1호
• /
• pp.28-32
• /
• 2013

Because the human voice is produced through vibration of the vocal cords during the exhalation of airflow, it is important to observe the vibration pattern of the vocal cords in patients complaining of voice changes. However, it is not easy to observe the actual vibration pattern of the vocal cord because it vibrates so fast that it cannot be observed by the naked eye and it is located deep in the throat. Recently, with advances in instruments, including laryngoscopes and video camera systems, the vibration pattern of the vocal cords can now be observed. However, considering that present video camera systems can detect 30-60 images per second and the vocal cord vibrates at 100-200 and 200-300 times per second in men and women, respectively, it is not possible to record the whole mucosal wave of the vocal cord in real time. To overcome this limitation, a stroboscope, which converts fast movements of the vocal cord into slower images, has been developed. Since then, several instruments were developed to examine vocal vibration pattern. However, each instruments have advantages and disadvantages. Therefore, we should know about these things to apply them in patients with voice problem.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5917-5935
• /
• 2018

Adaptive Multi-Rate Codec is one of the codecs which is used for making voice calls. It helps to connect people who are scattered in various geographical areas. It adjusts its bit-rate according to the user's channel conditions. It plays a vital role in providing an improved speech quality of voice connection in Long Term Evolution (LTE). There are some constraints which need to be addressed in providing this service profitably. Quality of Service (QoS) is the dominant mechanism which determines the quality of the speech in communication. On several occasions, number of users are trying to access the same channel simultaneously by standing in a particular region for a longer period of time. It refers to Multi-user channel sharing problem which leads to resource loss very often. The main aim of this paper is to develop a novel RSA - QoS scheduling algorithm for reducing the Resource Loss Ratio. Eventually, it increases the throughput.The simulation result shows that the RSA - QoS increases the number of users for accessing the resources better than the existing algorithms in terms of resource loss and throughput. Ultimately, it enhances the QoS in Mobile Networks.

• 한국국방경영분석학회지
• /
• 제26권1호
• /
• pp.56-69
• /
• 2000

A frequency assignment problem on time division duplex system is considered. Republic of Korea Army (ROKA) has been establishing an infrastructure of tactical communication (SPIDER) system for next generation and it will be a core network structure of system. VHF system is the backbone network of SPIDER, that performs transmission of data such as voice, text and images. So, it is a significant problem finding the frequency assignment with no interference under very restricted resource environment. With a given arbitrary configuration of communications network, we find a feasible solution that guarantees communication without interference between sites and relay stations. We formulate a frequency assignment problem as an Integer Programming model, which has NP-hard complexity. To find the assignment results within a reasonable time, we take a genetic algorithm approach which represents the solution structure with available frequency order, and develop a genetic operation strategies. Computational result shows that the network configuration of SPIDER can be solved efficiently within a very short time.

• 전자공학회논문지CI
• /
• 제41권2호
• /
• pp.51-64
• /
• 2004

표기 체계인 한글을 한국어 음가로 변환하는 음운변동 규칙을 역으로 적용하여, 한국어 음가를 한국어를 표기하는 문자 체계인 한글로 전환시키는 규칙을 고안하는 것이 본 연구의 목표이다. 제정된 규칙은 한국어 음성인식에 있어서 매우 귀중한 역할을 담당한다. 일반적인 음성인식 기법은 수회의 학습과정을 통하여 추출된 음성의 표준패턴과 인식 대상으로 입력된 음성을 비교하여 가장 유사한 패턴을 찾는 방법을 사용한다. 이 때 표준 음성패턴이 띄어쓰기 단위의 어절이라면 수백만 개의 표준 패턴이 수록되어야 하므로 표준패턴을 위한 방대한 데이터베이스의 구축은 물론 표준패턴과의 비교 회수도 너무 많아져서 실용화가 불가능하다. 이에 대한 대안인 음절 단위 인식의 경우는 인식된 음가가 실제의 한글 표기와 맞지 않으므로, 인식된 결과를 출력할 때에 실제의 한글표기로 변환해 주어야 하는 과제를 안게 된다. 이 과제를 해결하는 과정, 즉 일련의 한국어 음가들을 일련의 한글 표기 문자로 바꾸어 주는 과정에서는 본 논문에서 제안한 표준 한국어 음가 - 표기 문자 변환 규칙을 적용할 수 있을 것이다. 본 논문에서는 새롭게 제안된 표준 한글 음가-표기 문자 변환 규칙을 사용하여 한국어 음가를 한글 표기로 변환하는 시스템을 구현하였다. 그리고, 고안된 규칙의 무결성을 보이기 위하여 표준 발음규칙 30항을 반영하는 데이터 집합을 이용하여 구현된 시스템을 시험하였으며, 그 실험 결과를 제시한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.603-608
• /
• 2003

Recently, personal robots and home robots are developing by many companies and research groups. It is considered that a general effective interface for user of those robots is speech or voice. In this paper, Japanese speech based man-machine interface system is discussed for reflecting the fuzziness of natural language on robots, by using fuzzy reasoning. The present system consists of the derivation part of action command and the modification part of the derived command. In particular, a unique problem of Japanese is solved by applying the morphological analyzer ChaSen. The proposed system is applied for the motion control of a robot manipulator. It is proved from the experimental results that the proposed system can easily modify the same voice command to the actual different levels of the command, according to the current state of the robot.

• 음성과학
• /
• 제8권2호
• /
• pp.49-59
• /
• 2001

The phoneme segmentation is a very difficult problem in speech sound processing because it has found out segmental algorithm in many kinds of allophone and coarticulation's trees. Thus system configuration for the speech recognition and voice retrieval processing has a complex system structure. To solve it, we discuss a possibility of new segmental algorithm, which is called the minus a thirds one or plus in tripartitioning(삼분손익) of twelve temporament(12 율려), first proposed by Prof. T. S. Han. It is close to oriental and western musical theory. He also has suggested a 3 consonant and 3 vowel phonemes in Hunminjungum(훈민정음) invented by the King Sejong in the 15th century. In this paper, we suggest to newly name it as ortho-phonic phoneme(OPP/정음소), which carries the meaning of 'the absoluteness and independency'. OPP also is acceptable to any other languages, for example IPA. Lastly we know that this algorithm is constantly applicable to the global language and is very useful to construct a voice recognition and retrieval structuring engineering.

• Industrial Engineering and Management Systems
• /
• 제10권3호
• /
• pp.179-184
• /
• 2011

Recently, the fast development of communication technologies has brought a great convince for human beings' life. Lots of commercial services and transactions can be done by using mobile communication equipments such as smart phones. Consequently, smart phones have attracted lots of companies to invest them for their potential growth of market. Compared with basic feature phone, a smart phone can offer more advanced computing ability and connectivity. However, based on the responses of customers, there still are many defectives such as not friendly and smooth operation, short standby time of batteries, threat of virus infected and so on needed to be improved. Therefore, this study will propose a product innovative function development procedure into TRIZ (theory of inventive problem solving) to transform voice of customers into product design and to create novel functions, respectively. A case study of smart phones will be provided to illustrate the effectiveness of the proposed method.

• 스마트미디어저널
• /
• 제9권3호
• /
• pp.116-121
• /
• 2020

Digital Information Display와 KIOSK는 전용 컨텐츠의 개발 비용으로 인한 초기 도입 비용 및 유지 비용과 제품의 특성으로 인해 설치 비용이 높다는 문제가 있다. 이러한 문제를 해결하기 위해 오픈소스 하드웨어 및 이벤트 기반 논 블로킹 I/O 알고리즘을 사용하여 음성 전송 시스템을 설계하고 구현하였다. 제안하는 오픈 하드웨어를 통한 음성송출 시스템은 시스템 초기 도입 비용과 유지 보수비용이 저렴하고, 다양한 형태로 활용할 수 있어서 정보 취약 계층의 정보에 대한 접근성을 향상할 수 있다.

• 대한전자공학회논문지SP
• /
• 제38권5호
• /
• pp.567-575
• /
• 2001

본 논문에서는 음성신호의 발성길이와 상관없이 일정한 크기의 파라미터를 얻을 수 있는 새로운 방법을 제안하였다. 음성인식기의 성능은 음성신호에서 추출된 파라미터간의 유사도(패턴간의 거리)를 어떻게 비교하는지에 따라 결정된다. 그러나 화자에 따른 음성신호의 변이나 발성속도의 차이는 음성신호에서 일정한 크기의 파라미터 추출을 어렵게 한다. 제안한 방법은 음성신호에서 얻어진 파라미터를 스펙토그램의 형태로 표현한 뒤 2차원 DCT(Discrete Cosine Transform)를 이용해 일정한 크기의 파라미터로 정규화시키는 방법이다. 제안한 방법의 유효성을 입증하기 위해 청각세포를 모델링한 32개의 대역통과 필터로부터 얻어진 음성신호의 파라미터를 2차원 DCT 방법으로 가공한 후, 신경 회로망의 입력으로 사용하였다. 또한 기존 방법과의 인식률 비교를 위해 기존의 정규화된 입력을 구하는 방법 중 하나를 선택하여 비교 실험을 수행하였다. 실험결과 제안한 방법은 기존 방법에 비해 화자종속 및 화자독립 고립단어 인식에서 더 높은 인식률과 빠른 인식속도를 얻을 수 있었다.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• 제30권5호
• /
• pp.437-446
• /
• 2008

Electroglottography (EGG) is a simple and non-invasive technique for analyzing the vibratory patterns of the vocal folds by detecting impedance changes across the larynx. An abnormal electroglottogram is shown in patients who have a dysphagia associated with neuromuscular disorder. Electroglottography offers reliable informations for diagnosis of swallowing disorder and gives quantitative datas. The purpose of this study is to provide the normal value of electroglottography in normal adults. We took electroglottograms of 80 adults who have no problem in swallowing and utterance. EGG data were analyzed to find out the value of Pitch, Jitter and Closed quotient with a commercially available software. There were significant differences between a usual voice and loud voice in 3 measures on the EGG signalmean pitch, Avg. jitter, mean quotient. To get a proper electroglottography, phonation of a usual voice was better than a loud voice. Four measurements- S.D pitch, Avg. Jitter, Mean closed quotient, S.D closed quotient- were independent of sex for adult. Three measurements- Mean pitch, S.D pitch, Mean closed quotient - were independent of age for adult aged twenties to fifties. The Avg. Jitter of twenties appeared to be lower than those of forties and fifties. The S.D closed quotient of twenties appeared to be lower than those of thirties, forties and fifties.