• 전자공학회논문지B
• /
• 제30B권4호
• /
• pp.116-129
• /
• 1993

This paper proposes an on-line Recognition scheme of cursive Korean characters based on the DP matching and fuzzy concept. The proposed algorithm, invariant to rotation and size, reduces greatly the computational requirement of dynamic programming by matching phonemes rather than character patterns, where the angle difference and the ration of lengths between input and reference patterns are adopted as matching features. The correct matching of poorly written cursive characters becomes possible by introducing the fuzzy concept in representing the features of phonemes and the ralative position between adjacent phonemes. Computer simulation results are observed to show the effectiveness of the proposed algorithm.

• 전자공학회논문지B
• /
• 제29B권9호
• /
• pp.8-16
• /
• 1992

This paper presents a method which can recognized the Handwritten Korean characters by using a Context-Free Grammar. The input characters are thinned in order to dwindle the mount of data, the thinned characters are converted into one-dimension strings according to six-forms. when the point of contact among phonemes is found, two phonemes are seperated respectively by marking the index mark (\) at the points. The Context-Free Grammar to input characters is classified into group grammars concerning the similarity of phonemes, input characters are parsed by making use of the Pushdown automata method. As the bent parts in the Handwritten characters are found frequently, We try to correct the bent parts by using the parsing distance measure, which recognize characters according to minium value caused by measuring the weight distance between two sentences. In this experiment, the recognition rate shows 93.8% to 275 Handwritten Korean characters.

• 음성과학
• /
• 제8권3호
• /
• pp.185-200
• /
• 2001

This study was designed to investigate the treatment, generalization, and maintenance effects of vocal relaxation treatment on compensatory articulation(i.e., glottalization of plosive sound) of three children with cleft palate. Multiple baseline design was applied to evaluate treatment, generalization, and maintenance effects. The targeted phonemes were ph/, th/, /t/ which Were frequently substituted by glottal stop sounds. The main component of the treatment program was vocal relaxation using humming and aspiration sound /h/. The following conclusions were deduced from the results: (1) the treatment program for compensatory articulation was effective in facilitating correct production of targeted phoneme and eliminating glottalization for all subjects, (2) the treatment effects on articulation accuracy were generalized to untreated phonemes (/c/, /c$c^{h}$/) for 2 subjects, (3) the treatment effects on decrease of glottalization were generalized to untreated phonemes for all subjects, and (4) the treatment effects were maintained for all subjects for 2 weeks after treatment was terminated.

• 음성과학
• /
• 제8권3호
• /
• pp.51-73
• /
• 2001

This study starts with an investigation of the frequency of allophones from the narrowly transcribed data of (1) most frequently used 2000 words and (2) some passages of standard Seoul Korean. Consequently this entails the investigation of the frequency of phonemes by adding the number of allophones. These two investigations are conducted for the first time in the study of Korean phonology. Previous studies on the reported 'frequency of phoneme' are in fact studies on the 'frequency of letters' and the critical difference between these two types of studies has yet to be clarified accurately. This paper also reveals the proportional distribution of natural classes among Korean phonemes and letters.

• 음성과학
• /
• 제7권4호
• /
• pp.169-186
• /
• 2000

This paper aims to confirm the mispronunciation of native Korean students due to the phonetic and phonological system differences between English and Korean, and to find the works-to-do by experiment. Many Korean students tend to differentiate the sounds of word-final stop consonants not by vowel duration or the allophones but by the phoneme of the consonant itself. In English, Stop sounds change through the conditions of the aspirated, unaspirated, or unreleased sounds. But in Korean they are not allophones of phonemes but distinct phonemes. Therefore, many Korean students are apt to add an extra vowel sound /i/ after the final stop consonant in the eve form due to both the unperception of the differences between the phonemes and the allophones of stop consonants, and the influence of the Korean sound-sequence relationship. Since the replacement of the allophones and extra vowel addition does not change the meaning, the importance was almost lost. Nevertheless, this kind of study is essential for the precise learning and the use of the English language.

• 한국통신학회논문지
• /
• 제15권4호
• /
• pp.267-277
• /
• 1990

이 논문에서는 인공지능의 기본적인 문제풀이 기법인 상태공간 탐색을 이용하여 한글을 구성하는 기본자소를 분리하여 인식하는 방법을 제안하였다. 자소분리와 인식과정을 보다 밀접하게 결합하기 위하여 문제를 상태공간에 표현하고, 이 공간을 탐색하여 풀이하였다. 그리고 탐색효율을 향상시키기 위하여 한글의 조합규칙에 입각한 구조정보와 매트릭스 평면에서 각 자소가 갖는 위치정보를 이용하였으며, 컴퓨터실험을 통하여 그 유용성을 확인하였다.

• 대한전자공학회논문지
• /
• 제23권1호
• /
• pp.114-119
• /
• 1986

In this paper, an algorithm for the on-line recognition of handwritten Hangeul is proposed. The strokes are recognized by the minimum distance parser. The phonemes are separated by the finite-state automata resulted from the state graph of phonemes which are produced by the order of strokes. By simulation result for 3,000 characteristics in practical sentences, the recognition rate of strokes is obtained to be 98.5% and the separation rate of phonemes is obtained to be 92.5%.

• 음성과학
• /
• 제9권1호
• /
• pp.63-75
• /
• 2002

This paper examines the principles of the International Phonetic Association and its Alphabet to see if the International Phonetic Alphabet (the IPA, for short) is adequate for transcribing sounds of a language like Korean. Special attention is given to 'broad transcription' and it has been found that the IPA is inadequate in representing the phonemes: there is no way to correctly transcribe phonemically the sounds of Korean with the current alphabet. A suggestion is given to help solve this problem and extend the IPA to accommodate all the different languages of the world.

• 인터넷정보학회논문지
• /
• 제2권1호
• /
• pp.31-38
• /
• 2001

음소 단위로 구축된 음성 데이터는 음성인식과 음성합성 및 분석 등의 분야에서 매우 중요한 문제이다. 일반적으로 음소는 유성음과 무성음으로 구분된다. 이러한 유성음과 무성음은 많은 특징적 차이가 있지만, 기존의 음소 경계 검출 알고리즘은 이를 고려하지 않고 시간 축을 기준으로 이전 프레임과의 스펙트럼 비교만을 통하여 음소의 경계를 결정한다. 본 논문에서는 음소 경계 검출을 위하여 유성음과 무성음의 특징적 차이를 고려한 블록기반의 분류 알고리즘을 설계하였다. 분류 알고리즘을 사용하기 위한 스펙트럼 비교 방법은 MFCC(kel-Frequency Cepstrum Coefficient)를 기반으로 한 거리 측정 법을 사용하였고 유성음과 무성음의 구분은 에너지 영 교차율, 스펙트럼 비, 포만트 주파수를 이용하였다. 본 논문의 실험결과 3-4음절 고립단어를 대상으로 약 7%,의 정확도를 얻음으로써 기존의 음소 경계 검출 시스템보다 약 8%의 정확도 향상을 보였다.

• 정보처리학회논문지B
• /
• 제10B권6호
• /
• pp.665-672
• /
• 2003

본 논문에서는 단위음소들의 연결을 통한 음성합성 방법에 관하여 기술한다. 이때, 발생하는 가장 큰 문제점은 두 단위음소 사이의 연결부분에서 불연속이 발생하는 것이며, 특히 다른 화자로부터 녹음한 단위음소의 연결에서 불연속이 많이 발생한다. 이 문제를 해결하기 위하여 본 논문에서는 군집화된 다이폰을 이용하며, 포만트 궤적과 스펙트럼의 분포특성을 사용할 뿐 아니라 인간의 청각적인 특성을 반영하여 스펙트럼을 완만화하는 방법을 제안한다. 즉, 제안하는 방법은 단위음소 연결구간의 스펙트럼 분포특성의 유사도를 사용하여 단위음소들을 군집화하고 단위음소의 연결 구간에서 인간의 청각신경 특성을 고려하여 완만화의 양과 범위를 결정한 다음, 두 다이폰 경계의 스펙트럼 분포를 시간에 따라 가중치를 다르게 주어 스펙트럼 완만화를 수행한다. 이 방법은 불연속을 제거하며 완만화로 인하여 발생할 수 있는 음성의 왜곡을 최소화한다. 제안하는 방법의 성능을 평가하기 위하여 5명으로부터 녹음한 20개의 문장 중에서 추출한 500여 개의 다이폰을 사용하여 실험을 수행하였다.