• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.591-600
• /
• 2016

Computing technologies are increasingly applied to most casual human environment networks, as computing technologies are further developed. In addition, the rapidly increasing interest in IoT has led to the wide acceptance of speech recognition as a means of HCI. In this study, we present a novel method for recognizing the Korean vowel 'ㅜ', as a part of a phoneme based Korean speech recognition system. The proposed method involves analyses of bulk indicators calculated in the time domain instead of analysis in the frequency domain, with consequent reduction in the computational cost. Four elementary algorithms for detecting typical waveform patterns of 'ㅜ' using bulk indicators are presented and combined to make final decisions. The experimental results show that the proposed method can achieve 90.1% recognition accuracy, and recognition speed of 0.68 msec per syllable.

• Speech Sciences
• /
• v.13 no.3
• /
• pp.67-82
• /
• 2006

The purpose of this experimental study is to investigate formant characteristics of Korean monophthongs spoken by Japanese learners and to compare the characteristics of vowels produced by the Japanese learners with those of the Korean native speakers. The data consisted of three categories: eight vowels in isolation, words including eight vowels in carrier sentences, and words including eight vowels in natural sentences. In this study, formant frequencies of the vowels were measured by Wave Surfer. It was assumed that the formant frequencies of the Korean vowels produced by the Japanese learners could be different from those of the Korean native speakers due to the influence of their own Japanese vowels. Results of this study showed that the Japanese learners had the difficulties to distinguish between the pairs /-/and /ㅜ/, /ㅓ/and /ㅗ/, and /ㅏ/and /ㅔ/. In Japanese vowels, F2 frequency value of /ㅜ/ was similar to that of the Korean /-/. It means that when the Japanese leaners produced Korean /ㅜ/, they might neutralize /-/ and /ㅜ/. Besides, there were not /ㅓ/and /ㅐ/ in Japanese vowels. Therefore, they tended to pronounce /ㅓ/ similar to /ㅗ/ which has the most similar formant frequency value with that of /ㅓ/, and /ㅐ/ was pronounced similar to /ㅔ/ for the same reason.

• Phonetics and Speech Sciences
• /
• v.12 no.1
• /
• pp.33-42
• /
• 2020

This study identified the substitution of /u/ for /o/ (e.g., pyəllo [pyəllu]) in Korean based on the speech corpus as a function of grammar items. Korean /o/ and /u/ share the vowel feature [+rounded], but are distinguished in terms of tongue height. However, researchers have reported that the merger of Korean /o/ and /u/ is in progress, making them indistinguishable. Thus, in this study, the frequency of the phonetic manifestation /u/ of the underlying form of /o/ for each grammar item was calculated in The Korean Corpus of Spontaneous Speech (Seoul Corpus 2015) which is a large corpus from a total of 40 speakers from Seoul or Gyeonggi-do. It was then confirmed that linking endings, particles, and adverbs ending with /o/ in the word-final position were substituted for /u/ approximately 50% of the stimuli, whereas, in nominal items, they were replaced at a frequency of less than 5%. The high rates of substitution were the special particle "-do[du]" (59.6%) and the linking ending "-go[gu]" (43.5%) among high-frequency items. Observing Korean pronunciation in real life provides deep insight into its theoretical implications in terms of speech recognition.

• Journal of Korean Ophthalmic Optics Society
• /
• v.3 no.1
• /
• pp.181-188
• /
• 1998

In order to examine the legibility of the Hangul letters which is a syllabic, the three kind of visual charts were made of the ninety eight($14{\times}7$) Hangul Gothic type letters by the laser printer. These Hangul letters were constructed with the 13 consonant letters which are 'ㄱ, ㄴ, ㄷ, ㄹ, ㅁ, ㅂ, ㅅ, ㅇ, ㅈ, ㅋ, ㅌ, ㅍ, ㅎ', and the 6 vowel letters which are 'ㅏ, ㅓ, ㅗ, ㅜ, ㅡ, ㅣ'. The two examination methods were used, One is the discriminating the letters on the visual chart by men having 1.5 visual acuity. The other is the using the laser printer's resolution. Obtained data by these examination methods are the minimum readable size values of the letters and the maximum readable distance values from the reader to the objects. From these data the relative legibility of the Hangul letters were calculated, where the letter ㄱ was chosen for the standard. This resultant data were analyzed. In this result, the mean legibility of these Hangul letters descended in the order of 'ㄱ, ㄴ, ㅅ, ㄷ, ㅈ, ㅇ, ㅁ, ㅋ, ㅌ, ㅍ, ㅎ' Which are the consonant letters being in these letters. And the mean legibility descended in 'ㅣ, ㅡ, ㅏ, ㅗ, ㅓ, ㅜ' order. The mean legibility is dependent on used consonant letter more then on used vowel.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.15 no.4
• /
• pp.239-252
• /
• 1993

This study was done to analyze phonetic dysfunction and the effect of orthognathic surgery to phonation in the patients of mandibular prognathism. 20 persons were chosen as normal group and 20 patients of mandibular prognathism as abnormal for this study. 5 vowel sounds-'ㅏ(a)', 'ㅔ(e)', 'ㅣ(i)', 'ㅗ(o)', 'ㅜ(u)' and 14 consonant sounds-'ㄱ(g)', "ㄴ(n), 'ㄷ(d)', 'ㄹ(l)', 'ㅁ(m)', 'ㅂ(b)', 'ㅅ(s)', 'ㅇ(ng)', 'ㅈ(j)', 'ㅊ(ch)', 'ㅋ(k)', 'ㅌ(t)', 'ㅍ(p)', 'ㅎ(h)', were checked. We recorded these sounds in the period of preopration, postop. 12 months, postop. 24 months. A Formant ratio and a length of consonant time were studied with discriminant analysis. As a result of the study, the following conclusion were gained. 1. As a result of the analysis on vowel dysfunction patiensts of mandibular prognathism, more than 80% of men patients showed the dysfunction in prelingual sound 'ㅔ(e)' and 'ㅣ(i)'. More than 70% of women patients showed the dysfunction in all vowel. 2. One year later from the orthognathic surgery, men patients showed a marked improvement in 'ㅏ(a)'. The next were 'ㅗ(o)', 'ㅜ(u)' and 'ㅣ(i)'. Women patients showed a marked improvement in 'ㅜ(u)'. 3. Two year later from the orthognathic surgery, men patients showed a marked improvement in prelingual sound 'ㅔ(e)' and postlingual sound 'ㅗ(o)'. Women patients showed a marked improvement in 'ㅏ(a)'. More than 20% of patients showed the phonetic improvement compared with the condition of the postop. 12 months. 4. As a result of the analysis on consonant dysfunction patient of mandibular prognathism. more than 80% of men patients showed the dysfunction in lingual sound 'ㅅ(s)'. Most women patients showed the dysfunction in labial sound 'ㅁ(m)' and lingual sound 'ㄴ(n)'. More than 50% of patients showed the dysfunction in labial sound and lingual sound. 5. One year later from the orthognathic surgery. men patients showed a complete improvement in hard palatal sound 'ㅈ(j)'. The next were labial sound 'ㅂ(b)', lingual sound 'ㅅ(s)', soft palatal sound 'ㄱ(g)' and 'ㅋ(k)'. Women patients showed a marked improvement in soft palatal sound 'ㅇ(ng)' and 'ㄱ(g)'. 6. Two year later from the orthognathic surgery, all patients showed remarkable improvement in consonant sounds. except for labial sound 'ㅁ(m)', 'ㅍ(p)' and lingual sound 'ㄴ(n)'. The improvement ratio was increased as the time was going on compared with the condition of postop 12 months.

• Speech Sciences
• /
• v.11 no.3
• /
• pp.69-81
• /
• 2004

The purpose of this experimental study was to investigate characteristics of Korean vowels uttered by Japanese speakers. Eight Korean Vowels were uttered three times by ten male Korean and Japanese, female Korean and Japanese, respectively. Formant Frequencies were measured from sound spectrograms made by the Pitch Works. Results showed that female Japanese speakers uttered Korean vowels more similar to those uttered by Korean native speakers than did male Japanese speakers.. In particular, male Japanese speakers have articulatory problems pronouncing the back vowels(/ㅓ/, /ㅡ/, /ㅜ/). It appears that the width of male speakers' articulatory movements is comparatively narrower than those of female speakers.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.784-786
• /
• 2004

정보통신 단말기에서 한글을 입력할 때는 단말기에 부착되어 있는 한정된 개수의 입력키만 을 이용해야 한다는 제약이 있다. 이러한 제약 조건 하에서 한글 모음을 입력하는 효율적인 방법을 모색하기 위해 기본 모음 집합의 크기를 변화시키면서 모음 조합 방법을 제시하였다. 그 결과로 8개의 기본 모음 'ㅏㅓ ㅗ ㅜ ㅡ ㅣ ㅐ ㅔ' 로부터 모음의 조합 원리 및 가획 원리에 의해 입력키가 할당되지 않은 모음을 조합하는 방식을 제안하였다. 이 방법은 유사 모음간의 전환이 가능한 오류 수정 방식과 다중 입력 방식을 도입하여 사용자 편의성을 추구하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.907-909
• /
• 2004

정보화 시대가 진전됨에 따라 휴대폰과 리모콘 등 휴대용 단말기에서 한글을 입력할 필요성이 증가하고 있다. 휴대용 단말기에서 한글 입력 방식은 단말기에 부착되어 있는 제한된 버튼만을 이용해야 한다는 제약이 있다. 이러한 제약 조건 하에서 한글 모음을 편리하고 빠르게 입력할 수 있는 방법으로 'ㅏ/ㅓ/ㅗ/ㅜ/ㅡ/ㅣ/ㅐ/ㅔ'를 기본 요소로 하여 조합되는 모음의 입력 방식을 다양화하였으며, 기존의 천지인, 나랏글 방식과 비교했을 때 사용자 편의성과 입력의 신속성 측면에서 매우 효율적임을 확인하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.40-48
• /
• 2018

This paper proposes a license-plate recognition algorithm for automobile black-box image which is obtained from the camera moving with the automobile. The algorithm intends to increase the overall recognition-rate of the license-plate by increasing the Korean character recognition-rate using multi-stage neural network for automobile black-box image where there are many movements of the camera and variations of light intensity. The proposed algorithm separately recognizes the vowel and consonant of Korean characters of automobile license-plate. First, the first-stage neural network recognizes the vowels, and the recognized vowels are classified as vertical-vowels('ㅏ','ㅓ') and horizontal-vowels('ㅗ','ㅜ'). Then the consonant is classified by the second-stage neural networks for each vowel group. The simulation for automobile license-plate recognition is performed for the image obtained by a real black-box system, and the simulation results show the proposed algorithm provides the higher recognition-rate than the existing algorithms using a neural network.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1985.10a
• /
• pp.75-78
• /
• 1985

본 연구는 시간 영역의 parament를 이용하여 한국어 숫자음(영, 일, 이, 삼, 사, 오, 육, 칠, 팔, 구)을 인식했다. 입력 음성 신호 X(n)의 Beginning Point와 Ending point를 ZCR(Zero-crossing Rate), Magnitude, Energy, Autocorrelation을 이용 Beginning point와 Ending point를 구하고 자음부의 인식은 위 계수들을 이용하여 행했다. 또, 유성음 부분에서는 PARCOR(Partial Autocorrelation), LPC(Linear Predictive Coding)를 이용 모음부와 유성자음을 인식하여 모음을 6개 부류(ㅏ, ㅑ, ㅗ, ㅜ, ㅠ, ㅣ)로 구분 인식했다. 이 방법에 의하면 입력 음성 신호 X(n)의 B.P(Beginning Point)와 E.P(Ending Point)를 쉽게 추출 가능하며 또한 각 Parameter를 이용하여 94.4%의 인식율을 얻었다.