• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.75-78
• /
• 2000

본 논문은 자연스러운 합성음 생성을 위한 끊어 읽기 강도 예측에 관한 것으로, 문장에 대한 품사열이 주어졌을 때 Posteriori 확률을 최대화하는 끊어 읽기 강도를 비터비 디코딩으로 예측한다. 훈련용 데이터는 여성화자 1인이 발성한 2,100 문장이며, 음성 데이터로부터 휴지길이(pause)에 따라 끊어 읽기 강도를 2단계로 할당하고, 텍스트에서는 30개의 품사 태그 심볼을 이용하여 형태소분석 및 태깅을 수행하였다. 관측확률은 3개 연속하는 품사열이 발생할 확률로 하고 끊어 읽기 강도 천이확률은 bigram으로 했을 때, cross validation 방법으로 성능 평가를 수행하였다 평가결과, 훈련데이타에 대해서는 $89.7\%$, 테스트 데이터에 대해서는 $84.9\%$의 예측정확률을 보였다.

• English Language & Literature Teaching
• /
• v.10 no.2
• /
• pp.113-132
• /
• 2004

This study aims to suggest desirable directions through analyzing English test items of college entrance examinations(CEE) in Korea, China, and Japan. To achieve this, English test items of Scholastic Ability Test(SAT) in Korea were compared with those of CEE in China and Japan, and test items of TOEFL and IELTS. It was found that there were not many items for testing productive skills relatively to the tests of other countries including TOEFL and IELTS. Especially, there were integrated items for writing test in China. In case of speaking test, all the other country adopted direct ways like interview and oral test, not indirect test as in the SAT in Korea. It is suggested that there need to be included test items comprising long passages in order to measure extensive reading ability. It can be suggested that doze test be adopted for testing integrated proficiency of English.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.95-98
• /
• 2007

This study investigates pause positions of Korean students' reading of an English script. 12 natives speakers of English and 18 Korean students were asked to read The North Wind and the Sun. The common pause positions were determined by examining the pauses of the native speakers' readings. Korean students were asked to mark pauses on a script. And then they were trained to put pauses as native speakers of English do. Although some errors have been corrected after the training, others have not been corrected in Korean students' readings. Korean students made fewer errors in marking on the script than in reading the script. They seem to know where to put pauses, but lack of practice makes it difficult to put pause in the right positions when they read. That suggests that teachers should continue to teach students where to put pauses in their reading or speaking English.

• English Language & Literature Teaching
• /
• v.10 no.2
• /
• pp.43-65
• /
• 2004

In the comprehension of English texts, Korean students generally try to translate English into Korean in accordance with the word order of Korean language. As a result, the comprehension of English texts is made in a regressive way, which results in slower reading. In order to enhance the reading speed, it is necessary for students to practice progressive reading. Also, while reading English texts, most readers' eyes tend to look at one word at a time, which actually cuts down on the reading speed. Reading by the sense group of as many words as possible at a glance, however, can help a reader more efficiently in less time. This research aims at developing the Powerpoint program for progressive reading by the sense group according to the student's level. In this program, as for methodology, the technique of rooking it fade-away is introduced to force a reader's eyes to move fast. Through this technique, it is possible to make a line of the texts disappear on the screen and make another line appear, which enables a reader to sweep the words across each and every line of the reading material smoothly without regression.

• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.73-76
• /
• 2012

영어 교육의 필요성이 증가하고 그에 대한 수요가 늘어남에 따라 컴퓨터를 이용한 외국어 교육 시스템이 개인적인 영어 교육방법으로 소개되고 있다. 새로운 외국어를 접할 때 습득하기 어려운 부분 중 하나가 발음이고, 발음이 외국어 말하기 실력에 중요한 요소이기 때문에 특별한 훈련이 필요하다. 본 논문에서는 이러한 문제점에 대하여 충분히 인지하고 외국어 발음 향상에 도움을 주기 위하여 컴퓨터 보조 발음 훈련시스템을 개발하였다. 본 시스템은 발음 훈련과 억앙 훈련, 즉 문장 강세 훈련과 끊어 읽기 훈련을 포함하며, 사용자의 발화에 대해 적절한 평가와 피드백을 제공한다. 본 논문에서는 발음 훈련 시스템의 구성요소와 동작에 대하여 중점적으로 기술하였다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.14-18
• /
• 2023

본 연구는 한국어 음성-텍스트 데이터에서 보편적으로 나타난 휴지의 실현 양상을 분석하고, 이를 토대로 데이터셋을 선별해 보편적이고 규격화된 한국어 휴지 예측을 위한 모델을 제안하였다. 이를 위해 전문적인 발성 훈련을 받은 성우 등의 발화가 녹음된 음성-텍스트 데이터셋을 수집하고 MFA와 같은 음소 정렬기를 사용해 휴지를 라벨링하는 등의 전처리를 하고, 다양한 화자의 발화에서 공통적으로 나타난 휴지를 선별해 학습데이터셋을 구축하였다. 구축된 데이터셋을 바탕으로 LLM 중 하나인 KULLM 모델을 미세 조정하고 제안한 모델의 휴지 예측 성능을 평가하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.75-84
• /
• 2012

HMM-based Text-to-Speech systems generally utilize context dependent tri-phone units from a large corpus speech DB to enhance the synthetic speech. To downsize a large corpus speech DB, acoustically similar tri-phone units are clustered based on the decision tree using context dependent information. Context dependent information includes phoneme sequence as well as prosodic information because the naturalness of synthetic speech highly depends on the prosody such as pause, intonation pattern, and segmental duration. However, if the prosodic information was complicated, many context dependent phonemes would have no examples in the training data, and clustering would provide a smoothed feature which will generate unnatural synthetic speech. In this paper, instead of complicate prosodic information we propose a simple three prosodic boundary types and decision tree questions that use rising tone, falling tone, and monotonic tone to improve naturalness. Experimental results show that our proposed method can improve naturalness of a HMM-based Korean TTS and get high MOS in the perception test.