• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.28-33
• /
• 2000

This paper investigates the durational difference between syllable final segment and syllable initial one within word level. The Korean consonant (m) and (nn) were focused mainly. It could hardly say that there was significant difference between preceding consonant and following one, but it was observed that the preceding consonant tended to be shorter than the following one in the (mm) case. This might be explained by the fact that bilabial sound should appear at the first step of language acquisition. This leads to the conclusion that the articulation of preceding (m) shall be easier than others. In the case of alveolar geminate (nn), there was considerable statistic difference between preceding and following segments. It tends to be that the preceding consonant has longer duration.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.447-450
• /
• 2019

본 논문은 한국어 문장의 감성 분류를 위해 문장의 형태소, 음절, 자소를 입력으로 하는 합성곱층과 DenseNet 을 적용한 Text Multi-channel DenseNet 모델을 제안한다. 맞춤법 오류, 음소나 음절의 축약과 탈락, 은어나 비속어의 남용, 의태어 사용 등 문법적 규칙에 어긋나는 다양한 표현으로 인해 단어 기반 CNN 으로 추출 할 수 없는 특징들을 음절이나 자소에서 추출 할 수 있다. 한국어 감성분석에 형태소 기반 CNN 이 많이 쓰이고 있으나, 본 논문에서 제안한 Text Multi-channel DenseNet 모델은 형태소, 음절, 자소를 동시에 고려하고, DenseNet 에 정보를 밀집 전달하여 문장의 감성 분류의 정확도를 개선하였다. 네이버 영화 리뷰 데이터를 대상으로 실험한 결과 제안 모델은 85.96%의 정확도를 보여 Multi-channel CNN 에 비해 1.45% 더 정확하게 문장의 감성을 분류하였다.

• Journal of Ecology and Environment
• /
• v.29 no.3
• /
• pp.219-225
• /
• 2006

To study song themes and variation of Yellow-throated Bunting, we obtained and analyzed recordings from 45 males breeding in 16 deciduous forests of 6 provinces. We classified the 3,245 songs into a total of 164 song themes and 1,024 song variants according to the identification on the base of difference(lexicon) in 640 syllable compositions. Males had one to six song themes and averaged 3.5 themes. No males shared an identical song theme. Males had $5{\sim}14$ syllables (ave. 9.4) in one song theme and males increased effectively their repertoire size by changing syllable composition (i.e. adding, deleting, or substituting one or more syllables) in a single song theme. The number of variants averaged 5.1 (range 1 to 31) per song theme. Individual variability was highest in the terminal elements of the song. In PCA, the 16 populations are clearly separated on Co. I based on shared syllable and on Co. II based on unique syllable. Similarity of songs based on shared syllables by distance coefficients, showed a pattern of concordance with geography. Pairwise similarity declined with increasing distance among recording sites. 16 different geographical regions by the syllable were divided in UPGMA tree.

• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.1-10
• /
• 2022

The Korean polysemic ending '-(eu)lgeol' can has two different meanings, 'guess' and 'regret'. These are expressed by different boundary-tone types: a rising tone for guess, a falling one for regret. Therefore the sentence-final boundary-tone type is the most salient prosodic feature. However, besides tone type, the pitch difference between the final and penultimate syllables of '-(eu)lgeol' can also affect semantic discrimination. To investigate this aspect, we conducted a perception test using two sentences that were morphologically and syntactically identical. These two sentences were spoken using different boundary-tone types by a Korean native speaker. From these two sentences, the experimental stimuli were generated by artificially raising or lowering the pitch of the boundary syllable by 1Qt while fixing the pitch of the penultimate syllable and boundary-tone type. Thirty Korean native speakers participated in three levels of perceptual test, in which they were asked to mark whether the experimental sentences they listened to were perceived as guess or regret. The results revealed that regardless of boundary-tone types, the larger the pitch difference between the final and penultimate syllable in the positive direction, the more likely it is perceived as guess, and the smaller the pitch difference in the negative direction, the more likely it is perceived as regret.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.79-83
• /
• 2018

본 논문은 한국어 문장의 형태소, 음절, 자소를 동시에 각자 다른 합성곱층을 통과시켜 문장의 감성을 분류하는 Multi-channel CNN을 제안한다. 오타를 포함하는 구어체 문장들의 경우에 형태소 기반 CNN으로 추출 할 수 없는 특징들을 음절이나 자소에서 추출 할 수 있다. 한국어 감성분석에 형태소 기반 CNN이 많이 쓰이지만, 본 논문의 Multi-channel CNN 모델은 형태소, 음절, 자소를 동시에 고려하여 더 정확하게 문장의 감성을 분류한다. 본 논문이 제안하는 모델이 형태소 기반 CNN보다 야구 댓글 데이터에서는 약 4.8%, 영화 리뷰 데이터에서는 약 1.3% 더 정확하게 문장의 감성을 분류하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.267-271
• /
• 1998

신경망에 의한 음절과 연속음성 인식시 동특성처리의 한방법으로 회귀신경망을 이용한다. 본 연구는 비회귀형 상위은닉층과 회귀형 하위은닉층을 가진 4층 구조의 다층회귀신경망으로 예측기를 반들어 나성화자 5명이 CV형 음절 14개, CVC형 음절 14개를 각각 5회씩 발음한 총 700개의 음성중 3회분인 420개 음성으로 학습한 후 나머지 2회분인 280개 음성으로 인식을 평가한다. 입력신호의 예측차수와 상, 하위 은닉층으 뉴런수를 변경시키면서 각각의 인식률을 조사해 본 결과 상위 은닉층의 뉴런이 10개이고 하위 은닉층의 뉴런이 10개와 15개 그리고 예측차수가 3,4차일 때 가장 양호한 인식기로 동작한다는 것을 알 수 있었다. 이 때 나타난 인식률은 Elman 망보다 다소 우세하다.

• Annual Conference on Human and Language Technology
• /
• 1994.11a
• /
• pp.113-118
• /
• 1994

한국어 정보처리를 효율적으로 수행하기 위해서는 단어의 검색시간을 최소화하여야 한다. 그러나 기존의 방법들은 단어의 삽입과 삭제가 불가능하거나 검색시간이 길다는 단점을 가지고 있다. 본 논문에서는 탐식시간을 최소화하기 위해서 이중 배열을 가지는 이중 트라이를 이용하여 음절 및 자소단위의 검색방법에 관하여 논의한다. 검색시간에 있어서는 음절단위의 방법이 자소단위의 방법보다 빠르지만 기억장소는 자소단위의 방법이 음절단위의 방법보다 효율적이다. 자소단위의 방법에서 하나의 트라이를 여러개로 분할하여 저장함으로써 기억장소를 절반으로 줄일 수 있어 기억장소를 보다 효율적으로 이용할 수 있다.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4
• /
• pp.5-11
• /
• 1996

In this study, the method of speaker adaptation for uttered sentence using syllable unit hmm is proposed. Segmentation of syllable unit for sentence is performed automatically by concatenation of syllable unit hmm and viterbi segmentation. Speaker adaptation is performed using MAPE(Maximum A Posteriori Probabillity Estimation) which can adapt any small amount of adaptation speech data and add one sequentially. For newspaper editorial continuous speech, the recognition rates of adaptation of HMM was 71.8% which is approximately 37% improvement over that of unadapted HMM

• Journal of Convergence Society for SMB
• /
• v.6 no.4
• /
• pp.51-57
• /
• 2016

This study aims at investigating and comparing the vowel lengths of the eight stressed syllable vowels among the Korean college students with the English native speakers. To do this English sentences were uttered and recorded by twenty Korean subjects. Acoustic features were measured from a sound spectrogram with the help of the Praat software program and analyzed through statistical analysis. From the results of the experiment, I was able to find out that the differences of the lengths of the first syllable stressed vowels were significant. Especially in the pronunciation of the English front low vowel /${\ae}$/, native subjects pronounced significantly longer than Korean subjects, and this result could be used as a teaching material in pronunciation class.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.3
• /
• pp.47-56
• /
• 1999

Various phonological alteration occurs when we pronounce continuously in korean. This phonological alteration is one of the major reasons which make the speech recognition of korean difficult. This paper presents a rule-based system which converts a speech recognition character string to a text-based character string. The recovery results are morphologically analyzed and only a correct text string is generated. Recovery is executed according to four kinds of rules, i.e., a syllable boundary final-consonant initial-consonant recovery rule, a vowel-process recovery rule, a last syllable final-consonant recovery rule and a monosyllable process rule. We use a x-clustering information for an efficient recovery and use a postfix-syllable frequency information for restricting recovery candidates to enter morphological analyzer. Because this system is a rule-based system, it doesn't necessitate a large pronouncing dictionary or a phoneme dictionary and the advantage of this system is that we can use the being text based morphological analyzer.