• 대한음성학회지:말소리
• /
• 제51호
• /
• pp.17-37
• /
• 2004

The purpose of this dissertation is to make the general korean speakers to learn the standard pronunciations. But it is in existence that the obstructions of the command of the standard pronunciations. They are the mistake in the education course on the korean pronunciations, the teacher's capability and the mass communications's duplicity. To overcome this obstructions, we must concentrate our efforts on the propagation of the standard pronunciations. To propagate of the standard pronunciations we can take a several method. These are the presentation of the pronunciation mistakes, audio-visual teaching, the presentation of the pronunciation principles and the use of the korean dictionary. The standard pronunciations are different from the pronunciations of the general korean speakers in many respects. So we can't make an accurate estimate of the pronunciation's changes. No one knows what will happen in the future about the korean pronunciations. But we must teach the standard pronunciations to the general korean speakers. The standard pronunciations are offically valid in the present time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3257-3269
• /
• 2020

Articulation disorders are characterized by an inability to achieve clear pronunciation due to misuse of the articulators. In this paper, a method of detecting such disorders by comparing to the standard pronunciations is proposed. This method defines the standard pronunciations from the speeches of normal children by clustering them with three features which are the Linear Predictive Cepstral Coefficient (LPCC), the Mel-Frequency Cepstral Coefficient (MFCC), and the Relative Spectral Analysis Perceptual Linear Prediction (RASTA-PLP). By calculating the distance between the centroid of the standard pronunciation and the inputted pronunciation, disordered speech whose features locates outside the cluster is detected. 89 children (58 of normal children and 31 of children with disorders) were recruited. 35 U-TAP test words were selected and each word's standard pronunciation is made from normal children and compared to each pronunciation of children with disorders. In the experiments, the pronunciations with disorders were successfully distinguished from the standard pronunciations.

• 비교문화연구
• /
• 제38권
• /
• pp.405-431
• /
• 2015

The purpose of this paper is to investigate how to decide pronunciation of loanwords in Korean language. There has not been a regulation for pronunciation of loanwords in Korean language. Even the dictionary published by the government does not provide any information about the pronunciation of loanwords. In this paper, some actual solutions are suggested for the pronunciation of loanwords. Korean language has Regulations of Standard Korean, Korean Orthography, Regulations on Hangeul Transcriptions on Loanwords and Pronunciation Methods of Standard Korean. These language standards could help to decide pronunciation of loanwords. Some pronunciations which could not be regulated by them must be presented in the standard pronunciation dictionary. For example, glottalization rule of 's' in many loanwords could be presented in the description of each loanword in the dictionary. However the pronunciation of loanwords must be similar to the spelling. If various pronunciations are allowed to one spelling, then people will be so confused by the discrepancy between pronunciation and spelling of loanwords.

• 말소리와 음성과학
• /
• 제7권3호
• /
• pp.139-149
• /
• 2015

This paper aims to analyze pronunciation variations of loanwords produced by Korean and improve the performance of pronunciation modeling of loanwords in Korean by using syllable-based segmentation and phonological knowledge. The loanword text corpus used for our experiment consists of 14.5k words extracted from the frequently used words in set-top box, music, and point-of-interest (POI) domains. At first, pronunciations of loanwords in Korean are obtained by manual transcriptions, which are used as target pronunciations. The target pronunciations are compared with the standard pronunciation using confusion matrices for analysis of pronunciation variation patterns of loanwords. Based on the confusion matrices, three salient pronunciation variations of loanwords are identified such as tensification of fricative [s] and derounding of rounded vowel [ɥi] and [$w{\varepsilon}$]. In addition, a syllable-based segmentation method considering phonological knowledge is proposed for loanword pronunciation modeling. Performance of the baseline and the proposed method is measured using phone error rate (PER)/word error rate (WER) and F-score at various context spans. Experimental results show that the proposed method outperforms the baseline. We also observe that performance degrades when training and test sets come from different domains, which implies that loanword pronunciations are influenced by data domains. It is noteworthy that pronunciation modeling for loanwords is enhanced by reflecting phonological knowledge. The loanword pronunciation modeling in Korean proposed in this paper can be used for automatic speech recognition of application interface such as navigation systems and set-top boxes and for computer-assisted pronunciation training for Korean learners of English.

• 한국정보전자통신기술학회논문지
• /
• 제13권3호
• /
• pp.197-205
• /
• 2020

한국어는 자음과 모음과 같은 음소 단위의 발음은 고정되어 있고 표기에 대응하는 발음은 변하지 않기 때문에 외국인 학습자가 쉽게 접근할 수 있다. 그러나 단어와 어구, 문장을 말할 때는 음절과 음절의 경계에서 소리의 변동이 다양하고 복잡하며 표기와 발음이 일치하지 않기 때문에 외국어로서의 한국어 표준 발음 학습은 어려운 면이 있다. 그러나 영어 같은 다른 언어와 달리 한국어의 표기와 발음의 관계는 논리적인 원리에 따라 예외 없이 규칙화 할 수 있는 장점이 있으므로 발음오류에 대해 체계적인 분석이 가능한 것으로 여겨진다. 본 연구에서는 오류 발음과 표준 발음의 차이를 컴퓨터 화면상의 상대적 거리로 표현하여 시각화하는 모델을 제시한다. 기존 연구에서는 발음의 특징을 단지 컬러 또는 3차원 그래픽으로 표현하거나 입과 구강의 변화하는 형태를 애니메이션으로 보여 주는 방식에 머물러 있으며 추출하는 음성의 특징도 구간의 평균과 같은 점 데이터를 이용하는데 그치고 있다. 본 연구에서는 시계열로 표현되는 음성데이터의 특성 및 구조를 요약하거나 변형하지 않고 직접 이용하는 방법을 제시한다. 이를 위해서 딥러닝 기법을 토대로 자기조직화 알고리즘과 variational autoencoder(VAE) 모델 및 마코브 확률모델을 결합한 확률적 SOM-VAE 기법을 사용하여 클러스터링 성능을 향상시켰다.

• 대한한의학원전학회지
• /
• 제23권6호
• /
• pp.15-26
• /
• 2010

Objective This is a previous study for including traditional Korean medical terms into the UMLS(The Unified Medical Language System) and achieving the interoperability between various medical systems. Method First, the traditional medical terms were divided into 4 categories : basic theory, acupuncture, herb and formulae. And then, searching these terms through metathesaurus in UMLSKS(UMLS Knowledge Source Server), terminology information was investigated and analyzed. Results In the case of TM title, traditional Korean medicine was categorized as different semantic type from Traditional medicine, Traditional Chinese medicine and Kampo medicine. Acupuncture points were described only as abbreviation and herbs were conceptualized inconsistently, as some belonged to scientific name and some belonged to Chinese pronunciation. Formulaes are described as Chinese, Japanese and Korean pronunciations. Conclusions More research is needed on diagnosis/disease terms and semantic types for the unique concepts in traditional Korean medicine in order to including the international standard.

• 말소리와 음성과학
• /
• 제9권4호
• /
• pp.43-50
• /
• 2017

These days voice models of speech recognition software are sophisticated enough to process the natural speech of people without any previous training. However, not much research has reported on the use of speech recognition tools in the field of pronunciation education. This paper examined Google speech recognition of a short English paragraph produced by Korean college students in clear and casual speech styles in order to diagnose and resolve students' pronunciation problems. Thirty three Korean college students participated in the recording of the English paragraph. The Google soundwriter was employed to collect data on the word recognition rates of the paragraph. Results showed that the total word recognition rate was 73% with a standard deviation of 11.5%. The word recognition rate of clear speech was around 77.3% while that of casual speech amounted to 68.7%. The reasons for the low recognition rate of casual speech were attributed to both individual pronunciation errors and the software itself as shown in its fricative recognition. Various distributions of unrecognized words were observed depending on each participant and proficiency groups. From the results, the author concludes that the speech recognition software is useful to diagnose each individual or group's pronunciation problems. Further studies on progressive improvements of learners' erroneous pronunciations would be desirable.

• 한국문헌정보학회지
• /
• 제22권
• /
• pp.219-257
• /
• 1992

Among the Chinese Characters originated in Japan, some of them are very ancient in their origin and others come to exist as different forms by being used widely in forged books in Chinese. These Characters can be divided into three groups. First, the Chinese Characters whose forms are different. Most of these are 'hoiui' (회의)character, being made by imitating the forms of the original Chinese Letters. These characters do have meaning but not pronunciation. This is one distinct feature of Chinese Characters originated in Japan. Second, the Chinese Characters whose meaning has been assigned by the Japanese people. These letters can be grouped into two. One is the letters whose meanings are entirely different from original Chinese Characters, and the other is the letters whose meanings are not known although their pronunciations are known. It can be explained that the letters with different forms are made because of the ignorance of letter's existence. Or, the letters were made on purpose in ordoer to be used in different meanings. Third, the Characters with a partial modification of original Chinese Characters. Among the Characters in three groups above, pure Japanese-made Chinese Characters are those in group one and three since those in group two are Chinese Letters whose meanings (or pronunciation) only are Japanese. As a results of detailed investigation of pure Japanese-made Chinese Character in JIS X 0208-1990, the followings are discovered: 1. Pure Japanese-made Chinese Characters are 147 in numbers. 2. The Characters which were originally Chinese but now considered to be Japanese-made are 5 in numbers. Among these letters, 39 Characters are not listed in TaeHanHwaSaJon(Whose fame is well known as the authoritative dictionary of Chinese Characters), 47 Characters are not found in the dictionaries of Chinese Characters compiled in Korea. 3. 14 Characters seem to be Japanese-made Chinese Characters although it cannot be said so with accuracy because of various meanings found in several dictionaries of Chinese Characrters.

• 한국정보전자통신기술학회논문지
• /
• 제12권5호
• /
• pp.512-520
• /
• 2019

음성을 시각적으로 표현하는 것은 외국어를 습득하는 과정의 학습자나 음성을 직접 들을 수 없는 청각장애자에게 매우 유용하며 기존에 다수의 연구가 이루어졌다. 그러나 기존의 연구들은 발음의 특징을 단지 컬러로 표현한다든가 입모양을 3차원 그래픽으로 표현하거나 입과 구강의 변화하는 형태를 애니메이션으로 보여 주는 방식에 머물러 있다. 따라서 이런 방식을 사용하는 학습자들은 자신의 발음이 표준 발음과 얼마나 멀리 떨어져 있는지 알 수가 없고 더 나아가서 학습 중에 스스로 교정을 해 나가는 시스템을 개발하기가 기술적으로 어려운 단점이 있다. 이를 극복하기 위해 본 논문에서는 음성 간의 상대적 거리를 토대로 음성을 시각화하는 모델을 제시하고, 이를 한국어 모음에 적용하여 모음의 음성적 특징을 이용한 시각화의 구체적인 구현 방법을 제시한다. 음성데이터에서 F1, F2, F3의 세 개의 포먼트를 구하고 이들 특징벡터를 코호넨 자기조직화맵 알고리즘으로 2차원 화면에 사상하여 각 음성을 화면 위의 각 점에 대응하여 표현하였다. 제안하는 시스템의 실제적인 구현은 인터넷에 공개된 음성처리 공개소프트웨어를 사용하고 한국인 교사의 표준 발음과 한국어를 배우고 있는 외국인 유학생의 음성을 이용하여 음성특징의 상호간 거리를 구하였으며, 사용자 인터페이스는 자바스크립트를 이용하여 구현하였다.