• 한국인터넷방송통신학회논문지
• /
• 제18권3호
• /
• pp.127-134
• /
• 2018

본 논문에서는 한국어를 기반으로 음성 데이터와 텍스트 정보에서 한국어 음소를 추출하고 분할된 음소들을 사용하여 정확하고 자연스러운 3D 립싱크 애니메이션을 제작하기 위한 오토 립싱크 Maya 플러그인을 개발하였다. 여기서 개발된 시스템에서는 음소 분할은 Microsoft Speech API 엔진 SAPI에서 제공하는 49개의 음소를 참조하여 한글에 사용되는 음소들을 모음 8개, 자음 13개로 분류하였다. 또한 모음과 자음의 발음들은 다양한 입모양을 가지지만 일부 동일한 입모양에 대하여 같은 Viseme을 적용할 수 있도록 구현하였다. 이를 바탕으로 파이썬(Python) 기반의 오토 립싱크 Maya 플러그인을 개발하여 립싱크 애니메이션이 한 번에 자동으로 구현할 수 있게 하였다.

• 한국멀티미디어학회논문지
• /
• 제14권1호
• /
• pp.85-93
• /
• 2011

기존의 어휘 인식에서는 일반적인 벡터 값을 데이터베이스를 이용하여 구하므로 탐색 중에 형성되는 음소를 처리하지 못하는 문제점을 제공하며, 음소 데이터에 대한 모델을 구성할 수 없는 단점으로 인하여 가우시안 모텔의 정확성을 확보하지 못하게 된다. 따라서 본 논문에서는 음소가 갖는 특징을 기반으로 바타챠랴 거리 측정법을 이용하여 정확한 음소로 인식할 수 있도록 유도하였으며 유사 음소 인식과 오인식 오류를 최소화하여 인식률을 향상시켰다. 연속 확률 분포의 공유로부터 가우시안 모델 최적화를 실험한 결과 향상된 신뢰도로 인해 높은 인식 성능을 확인하였으며, 본 논문에서 제안한 바타챠랴 거리 측정법을 이용하여 실험한 결과 기존의 방법들에 비하여 평균 1.9%의 성능 향상을 나타내었으며 신뢰성을 바탕으로 인식율에서 평균 2.9%의 성능 향상을 나타내었다.

• 영어어문교육
• /
• 제11권4호
• /
• pp.97-120
• /
• 2005

Production and perception of second language sounds are typically influenced by second language learners' native language sounds. In this study we investigate how the Korean language influences Korean speakers' production of English alphabets. In the experiment conducted to prepare for this study 16 native speakers of Korean pronounced English alphabets. Then three native speakers of English evaluated the Korean subjects' pronunciation of them. The results show that the Korean subjects' native language (i.e., Korean) influences their production of the English alphabets. When Korean has sounds corresponding to English alphabets, the English subjects rate the Korean subjects' production of them good. For instance, Korean has voiceless stop phonemes, hence their production of English alphabets was rated good by the English subjects. The Korean subjects' production of English alphabets containing the sounds that do not exist in Korean was rated poor by the English subjects. For instance, Korean does not have voiced fricative phonemes, hence their production of English alphabets was rated poor.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 제11회 음성통신 및 신호처리 워크샵 논문집 (SCAS 11권 1호)
• /
• pp.395-398
• /
• 1994

In this paper the word recognition using sub-model based Hidden Markov Model was studied. Phoneme models were composed of 61 phonemes in therms of Korean language pronunciation characteristic. Using this, word model was maded by serial concatenation. But, in case of this phoneme concatenation, the second and the third phoneme of syllable are overlapped in distribution at the same time. So considering this, the method that combines the second and the third phoneme to one model was proposed. And to prevent the increase in number of model, similar phonemes were combined to one, and finially, 57 models were created. In experiment proper model structure of sub-model was searched for, and recognition results were compared. So similar recognition results were maded, and overall recognition rates were increased in case of using parameter tying method.

• 음성과학
• /
• 제12권3호
• /
• pp.185-200
• /
• 2005

The objective of this study is to examine acoustic cues in spoken French for the assessment of pronunciation which is necessary to realization of the multimedia system. The corpus is composed of simple expressions which consist of the French phonological system include all phonemes. This experiment was made on 4 male and female French native speakers and on 20 Korean speakers, university students who had learned the French language more than two years. We analyzed the recorded data by using spectrograph and measured comparative features by the numerical values. First of all, we found the mean and the deviation of all phonemes, and then chose features which had high error frequency and great differences between French and Korean pronunciations. The selected data were simplified and compared among them. After we judged whether the problems of pronunciation in each Korean speaker were either the utterance mistake or the interference of mother tongue, in terms of articulatory and auditory aspects, we tried to find acoustic features as simplified as possible. From this experiment, we could extract acoustic cues for the construction of the French pronunciation training system.

• 말소리와 음성과학
• /
• 제1권4호
• /
• pp.17-27
• /
• 2009

Despite many studies on the production and perception of L2 phonemes, studies on how such phonemes are encoded lexically remain scarce. The aim of this study is to examine whether L2 learners have a perceptual problem with L2 suprasegmentals which are not present in their L1, or if they are able to perceive but not able to encode them in their lexicon. Specifically, Korean learners were tested to see if they could discriminate the vowel length differences in Japanese at the psychoacoustic level through a simple AX discrimination task. Then, a speeded lexical decision task with high phonetic variability was conducted to see whether they could use such contrasts lexically. The results showed that Korean learners of Japanese have no difficulties in discriminating Japanese vowel length contrast, but they are unable to encode such contrast in their phonological representation, even with long L2 exposure.

• 한국음향학회지
• /
• 제8권5호
• /
• pp.86-94
• /
• 1989

본 논문에서는 새로운 음성표현 방법의 하나로 멜켑스트럼 계수에 대한 부호패턴(+,-)을 이용하는 방법을 제안한다. 부호패턴은 보음이나 비음과 같이 정상성이 강한 음성신호에 대해서 비교적 안정된 형태를 얻을 수 있으며, 음운성을 크게 손상시키지 않고 화자간 개인차를 흡수할 수 있다. 본 논문에서는 이러한 부호패턴을 이용하여 한국어 음소를 표현함으로써 음소모델의 작성과 음소의 인식절차를 크게 감소시킬 수 있음을 보인다.

• 한국음향학회지
• /
• 제8권5호
• /
• pp.70-77
• /
• 1989

본 연구는 한국어를 음소변로 분리하여 인식하는 실험에 관한 연구이다. 한국어 단음 545개를 자음 음소, 모음 음소, 받침 음소로 분리하여 선형 예측 계수로 인식한 결과, 각각 $87.3(\%), 91.0(\%), 91.7(\%)$의 인식률을 얻었고, 이 음소들을 결합한 단음에서는 $71.4(\%)$의 인식률을 얻었다. 음소 분리 및 음소 인식은 Itakura-Saito 거리 측정을 이용하였다.

• 한국음향학회지
• /
• 제8권1호
• /
• pp.81-87
• /
• 1989

본 논문은 Markov 모델에 의한 효과적인 한국어 음소모델 작성방식과 인식에 대하여 기술한다. hidden Markov 모델은 음성신호 고유의 비정상성을 효과적으로 모델화할 수 있다. 본 논문에서는 음소의 일련의 변화하는 특성, 즉 천이-안정-천이의 변화를 나타내기 위하여 3상태 음소모델을 제안한다. 또한 음소길이가 인식성능에 영향을 미치는 중요한 요소임을 밝히고 길이를 고려한 3상태 hidden Markov 모델을 사용하여 인식률을 개선시킬 수 있음을 보였다.

• 전자공학회논문지B
• /
• 제32B권1호
• /
• pp.171-179
• /
• 1995

In many continuous speech recognition systems, phoneme is used as a basic recognition unit However, the coarticulation generated among neighboring phonemes makes difficult to recognize phonemes consistently. This paper proposes allophone as an alternative recognition unit. We have classified each phoneme into three different allophone groups by the location of phoneme within a syllable. For a recognition algorithm, time-delay neural network(TDNN) has been designed. To recognize all Korean allophones, TDNNs are constructed in modular fashion according to acoustic-phonetic features (e.g. voiced/unvoiced, the location of phoneme within a word). Each TDNN is trained independently, and then they are integrated hierarchically into a whole speech recognition system. In this study, we have experimented Korean plosives with phoneme-based recognition system and allophone-based recognition system. Experimental results show that allophone-based recognition is much less affected by the coarticulation.