• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.369-374
• /
• 2020

동시통역은 원천텍스트의 의미를 잘 전달하는 것 뿐만 아니라, 순차통역이나 번역과 달리, 지연 시간없이 즉각적으로 번역하는 것이 매우 중요하다. 따라서 적절한 길이의 지점에서 원천텍스트를 분절해야 한다. 그러나 발화자마다 발화 속도가 서로 다르며, 이 발화 속도는 전체 발화에서 늘 일정하지 않기 때문에, 분절단위의 적절한 길이를 설정하는 것은 상당히 어려운 과제이다. 본 연구에서는 발화자마다 발화 속도가 다른 상황과 발화가 진행되는 동안 실시간으로 발화 속도가 변화하는 상황에 적응 가능한 동시통역 분절 방법론(개인화 기법)을 제안한다. 이를 위해 본 논문에서는 먼저 동시통역 데이터를 이용하여 기준 발화 속도를 설정하였다. 그 다음 이를 원천 발화의 현재 속도와 비교하여 실시간으로 해당 발화자에게 있어 최적의 분절길이가 얼마인지 계산한다. 제안한 개인화 기법의 효력을 검증하기 위해 실험을 진행하였고, 그 결과 개인화를 적용하면 분절 성능이 높아졌다.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.162-172
• /
• 2004

This study investigates the following three things through a production experiment and acoustic analysis: 1) relationship between speech rate and the segment duration in Korean, 2) relationship between speech rate and spectral characteristics of vowels, i. e. undershoot, and 3) correlation between the vowel duration and undershoot. The results showed that the faster the speech rate nab, the shorter the duration of syllables and segments was. A few speakers were affected by speech rate in the durational ratios between closure and aspiration in a stop and between Towel and consonant in a syllable. Closure duration and vowel duration were more affected compared to aspiration and consonant duration, respectively. Speakers showed some differences in the extent to which speech rate affected vowel undershoot, implying that speakers used different production mechanisms for spectral characteristics of vowels: Some speakers speeded up movement of articulatory organs according to speech rate increase while some kept it constant regardless of speech rate change.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.14-22
• /
• 2003

In this study, we examined the acoustic characteristics of Korean vowels through a production test under three conditions of speaking rates (slow, normal, fast). The effects of a change in speaking .ate on vowel duration were found to be very strong. The faster speaking rate was, the shorter the total duration of vowels was. But the duration ratio of two components of diphthong was not changed significantly according to changes in speaking rate. But unlike the temporal aspects, the formant value of vowels at their steady-state and change ratio of formant of semivowels were not affected strongly by the change in speaking rate.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.2
• /
• pp.63-72
• /
• 2012

The purpose of this paper is to provide basic data for development of Korean teaching programs for immigrant women from multicultural families through the acoustic analysis of their speech rate and pauses. They showed slower speech rate, longer pause duration, and higher frequency of pauses compared to a Korean women's group. Philippine women, whose residence duration in Korea is relatively longer than that of Vietnamese women, were more similar to Korean women. The slower speech rate of the immigrant women seems to be due to their slower articulation rate and their reading habit of inserting a pause after almost every word in a sentence.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.6
• /
• pp.1531-1540
• /
• 1997

In this paper, we presents automatic Korean continuous speech recognizer which is improved by the speech rate estimation and the compensation methods. Automatic continuous speech recognition is significantly more difficult than isolated word recognition because of coarticulatory effects and variations in speech rate. In order to recognize continuous speech, modeling methods of coarticulatory effects and variations in speech rate are needed. In this paper, the speech rate is measured by change of format, and the compensation is peformed by extracting relatively many feature vectors in fast speech. Coarticulatory effects are modeled by defining 514 Korean diphone set, and ETRI's 445 word DB is used for training speech material. With combining above methods, we implement automatic Korean continuous speech recognizer, which shows improved recognition rate, based on DHMM(Discrete Hidden Markov Model).

• Phonetics and Speech Sciences
• /
• v.15 no.4
• /
• pp.1-10
• /
• 2023

This study investigated the relative effectiveness of letter-based versus syllable-based measures of speech rate and articulation rate in predicting the articulation score, prosody fluency, and rating sum using "English speech data of Koreans for education" from AI Hub. We extracted and analyzed 900 utterances from the training data, including three balanced age groups (13, 19, and 26 years old). The study built three models that best predicted the pronunciation assessment scores using linear mixed-effects regression and compared the predicted scores with the actual scores from the validation data (n=180). The correlation coefficients between them were also calculated. The findings revealed that syllable-based measures of speech and articulation rates were more effective than letter-based measures in all three pronunciation assessment categories. The correlation coefficients between the predicted and actual scores ranged from .65 to .68, indicating the models' good predictive power. However, it remains inconclusive whether speech rate or articulation rate is more effective.

• Phonetics and Speech Sciences
• /
• v.14 no.2
• /
• pp.29-38
• /
• 2022

This study aimed to analyze the speech appearing in the National Institute of Korean Language's Daily Conversation Speech Corpus (2020) and reveal how the speech rate and the frequency of turn-taking affect the change in prosody units. The analysis results showed a positive correlation between intonation phrase, word phrase frequency, and speaking duration as the speech speed increased; however, the correlation was low, and the suitability of the regression model of the speech rate was 3%-11%, which was weak in explanatory power. There was a significant difference in the mean speech rate according to the frequency of the turn-taking, and the speech rate decreased as the frequency of the turn-taking increased. In addition, as the frequency of turn-taking increased, the frequency of intonation phrases, the frequency of word phrases, and the speaking duration decreased; there was a high negative correlation. The suitability of the regression model of the turn-taking frequency was calculated as 27%-32%. The frequency of turn-taking functions as a factor in changing the speech rate and prosodic units. It is presumed that this can be influenced by the disfluency of the dialogue, the characteristics of turn-taking, and the active interaction between the speakers.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.267-274
• /
• 2021

The purpose of this study is to investigate differences in learning flow and teaching presence according to the lecturer's appearance and the lecturer's speech rate. For this experiment, 183 freshman students from Xingtai University in China were selected as subjects of the experiment, and a total of four types of lecture videos were developed to test the lecturer's appearance and their speech rates. Data was analyzed through multivariate analysis of variance. According to the results of the analysis, first, learning flow and teaching presence of groups who experienced the presence of the lecturer appeared were significantly higher than the groups who learned without the appearance of the lecturer. Second, the groups who learned from videos with a fast speech rate showed higher learning flow and teaching presence than the group who learned at a slow speech rate. Third, there were no significant differences in both learning flow and teaching presence according to the lecturer's appearance and speech rate. This result provides a theoretical and practical basis for developing customized videos according to learners' characteristics.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1711-1714
• /
• 2015

스마트 디바이스가 사회와 소통할 수 있는 도구가 되었음에도 불구하고 아직까지 노인들이 사용하기에는 어려움이 있다. 여기에 음성인식 기술을 이용한 음성인터페이스를 활용함으로써 노인들의 스마트 디바이스에 대한 사용성을 높일 수 있다. 하지만 일반적인 음성인식 시스템은 청장년의 발성 스타일에 맞춰져 있기 때문에, 노화된 노인의 발성이 그대로 입력될 경우 음성인식률이 하락한다. 본 연구에서는 노인의 음절 별 발화속도가 일반적인 음성인식 시스템의 성능을 보증할 수 있는 범위를 벗어나는 경우가 많다는 분석 결과를 토대로 노인의 음절 별 발화속도를 조정한 결과 노인남녀 평균 음성인식률이 15.3% 상승하였다. 이처럼 노인의 음성인식 오류 원인들 중 하나인 발화속도의 재조정으로 음성 인식률을 높일 수 있는 토대를 마련하였다. 이는 노인들이 스마트 디바이스를 이용하여 쉽고 정확한 작업을 수행할 수 있게 됨으로써, 노인들의 사회 참여와 정보 획득이 용이해 지고 더 나아가 세대 간의 소통에도 이바지할 것으로 기대한다.

• Phonetics and Speech Sciences
• /
• v.14 no.3
• /
• pp.51-66
• /
• 2022

This study aims to help Korean English learners to learn English pronunciation by revealing which suprasegmentals affect the implementation of English sentences closer to native English speakers when they read English sentences. To this end, Korean middle school English learners were selected as subjects and research data were gathered through sentence types (declarative, interrogative, imperative, and exclamative), as well as syllables. Speech rate, pause frequency, pause duration, F0 range, and rhythm among suprasegmentals were used for analysis of these English sentence utterances. Mean analysis, correlation analysis, and regression analysis were performed. The results showed that speech rate, pause frequency, pause duration, and F0 range affected the evaluation of fluency levels. In the regression analysis between all suprasegmentals and fluency levels, the suprasegmentals that most affected fluency levels were speech rate and F0 range. Rhythm had no meaningful relation with fluency levels. Therefore, when teaching English pronunciation, it is necessary to teach students to increase their speech rate and F0 range. In addition, students should be trained to reduce both the number and the duration of pauses during utterance to improve their fluency. It is noteworthy that of the four sentence types, exclamative sentences were produced with faster speech rate, fewer pauses, shorter pause duration, and higher rhythm values.