• 대한음성학회지:말소리
• /
• 제63호
• /
• pp.101-112
• /
• 2007

Spoken dialog system development includes many laborious and inefficient tasks. Since there are many components such as speech recognition, language understanding, dialog management and knowledge management in a spoken dialog system, a developer should take an effort to edit corpus and train each model separately. To reduce a cost for editing corpus and training each model, we need more systematic and efficient working environment. For the working environment, we propose DialogStudio as a spoken dialog system workbench.

• 정보과학회 논문지
• /
• 제44권2호
• /
• pp.163-170
• /
• 2017

통계적 기계 번역을 이용한 구어-수화 번역 연구가 활발해짐에도 불구하고 수화 말뭉치의 자원 희소성 문제는 해결되지 않고 있다. 본 연구는 수화 번역의 첫 번째 단계로써 통계적 기계 번역을 이용한 구어-수지 신호 번역에서 말뭉치 자원 희소성으로부터 기인하는 문제점들을 해결할 수 있는 세 가지 전처리 방법을 제안한다. 본 연구에서 제안하는 방법은 1) 구어 문장의 패러프레이징을 통한 말뭉치 확장 방법, 2) 구어 단어의 표제어화를 통한 개별 어휘 출현 빈도 증가 및 구어 표현의 번역 가능성을 향상시키는 방법, 그리고 3) 수지 표현으로 전사되지 않는 구어의 기능어 제거를 통한 구어-수지 표현 간 문장 성분을 일치시키는 방법이다. 서로 다른 특징을 지닌 영어-미국 수화 병렬 말뭉치들을 이용한 실험에서 각 방법론들이 단독으로 쓰일 때와 조합되어 함께 사용되었을 때 모두 말뭉치의 종류와 관계없이 번역 성능을 개선시킬 수 있다는 것을 확인할 수 있었다.

• 한국융합학회논문지
• /
• 제12권1호
• /
• pp.57-63
• /
• 2021

사람의 발화 내용을 이해하도록 하는 언어 인식 시스템은 주로 영어로 연구되어 왔다. 본 논문에서는 시스템과 사용자의 대화 내용을 수집한 말뭉치를 바탕으로 언어 인식 시스템을 훈련시키고 평가할 때 사용할 수 있는 한국어 데이터셋을 개발하고, 관련 통계를 제시한다. 본 데이터셋은 식당 예약이라는 고정된 주제 안에서 사용자의 발화 의도와 슬롯 채우기를 해야 하는 데이터셋이다. 본 데이터셋은 6857개의 한국어 문장으로 이루어져 있으며, 표기된 단어 슬롯의 종류는 총 7개이다. 본 데이터셋에서 표기된 발화의 종류는 총 5개이며, 문장의 발화 내용에 따라 최대 2개까지 동시에 기입되어 있다. 영어권에서 연구된 모델을 본 데이터셋에 적용시켜 본 결과, 발화 의도 추측 정확도는 조금 하락하였고, 슬롯 채우기 F1 점수는 크게 차이나는 모습을 보였다.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2000년도 하계학술발표대회 논문집 제19권 1호
• /
• 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.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2004년도 춘계 학술대회 발표논문집
• /
• pp.215-218
• /
• 2004

The aim of this paper is to analyze the acoustic features for disguised voice. In this paper we examined the features such as pitch range, vowel formants(F1, F2, F3, F4). So the result of the analysis is as follows. : (1) Pitch range and average of pitch value is very important cue for speaker verification. (2) F3-F2 is also important cue for speaker verification (3) /a/ is more verified than other vowels.

• 인문언어
• /
• 제5권
• /
• pp.55-74
• /
• 2003

The issues concerning the nature of the attitude toward the study of national language may vary from country to country, depending on the national or racial characteristics. The problem domains and the methodologies dealing with them may vary accordingly. Ever since the Korean language was equipped with a writing system in the year of 1443 through King Sejong's long-cherished desire, investigations have been constantly made into the real nature of the language itself in pursuit of a better method for representing the spoken language in written form. This is how the study of the Korean language began to take shape. Among such investigations are Hunmin-jeong-eum(the Korean script: 1446) compiled by Jiphyon-jon, the royal office of schloarly researches, Doongguk-jeonghun-yokhun (the orthodox script of Korean: 1448), Hongmu-jeonghun-yeokhun(interlinear gloss for the Chinese script of the Ming Dynasty: 1455), An Orthodox Approach to Written Korean (1909) by the institute of the National Script, Re Standardized Spelling System (1933) by Chosun Language Society, An Authorized Dictionary of Standard Korean (1936), How to Write Borrowed Words(1940), and A Grand dictionary of Korea (1947-57). Chu Shi-Gyung's Phonetics of the Korean Script(1908), Korean Grammar(1910), and Sound Patterns of Korean(1914) were all written in this vein; so was Choi Hyun-Bae's Uri-mal-bon (the rudiments of Korean Grammar: 1929/1937). All these achievements in the study of the Korean language are the end-products of the constant endeavor to solve the issues related to the spoken and written farms of the Korean language. And this is how the uniqueness and autonomy of the language study in korea have been established. It should be borne in mind, however, that, in seeking solutions to the problems inherent in the Korean linguistic studies of foreign countries. On the contrary, they have been very active in accommodating such results. While they have set up their problem domains on the basis of the korean language, they been progressively open-minded in looking for the solutions to the problems at hand.

• 한국어교육
• /
• 제23권1호
• /
• pp.1-23
• /
• 2012

The development of corpus in recent years has attracted increased research on spoken Korean. Nevertheless, these research outcomes are yet to be meaningfully and adequately reflected in Korean language textbooks. The reported speech marker '-dae' is one of these areas that need more attention. This study investigates whether or not in textbooks '-dae' is clearly explained to English-speaking learners to prevent confusion and misuse. Based on a contrastive analysis of Korean and English, this study argues three points: Firstly, '-dae' should be introduced to Korean learners as an independent sentence ender rather than a contracted form of '-dago hae'. Secondly, it is necessary to teach English-speaking learners that '-dae' is not equivalent to the English report speech form. It functions more or less as a third person marker in Korean. Learners should be informed that '-dae' is used for statements in English, if those statements were hearsay but the source of information does not need to be specified. This is a very distinctive difference between Korean and English and should be emphasized in class when 'dae' is taught. Thirdly, '-dae' should be introduced before indirect speech constructions, because it is mainly used in simple statements and the frequency of '-dae' is very high in spoken Korean.

• 한국어교육
• /
• 제25권1호
• /
• pp.1-27
• /
• 2014

This study investigates how common English hedge expressions such as 'I think' and 'I guess' appear in Korean, with the aim of providing explicit explanation for English-speaking leaners of Korean. Based on a contrastive analysis of spoken English and Korean corpus, this study argues three points: Firstly, 'I guess' appears with a wider variety of modalities in Korean than 'I think'. Secondly, this study has found that Korean textbooks contain inappropriate use of registers regarding the English translations of '-geot -gat-': although these markers are used in spoken Korean, they were translated into written English. Therefore, this study suggests that '-geot -gat-' be translated into 'I think' in spoken English, and into 'it seems' in the case of written English and narratives. Lastly, the contrastive analysis has shown that when 'I think' is used with deontic modalities such as 'I think I have to', Korean use '-a-ya-get-': the use of hedge marker 'I think' with 'I have to', which shows obligation or speaker's volition turns the deontic modalities into expressions of speaker's opinion.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2002년도 하계학술발표대회 논문집 제21권 1호
• /
• pp.87-90
• /
• 2002

This paper analyzes statistically the relationship between size and balance of text corpus by evaluation of the effect of interview sentences in language model for Korean broadcast news transcription system. Our Korean broadcast news transcription system's ultimate purpose is to recognize not interview speech, but the anchor's and reporter's speech in broadcast news show. But the gathered text corpus for constructing language model consists of interview sentences a portion of the whole, $15\%$ approximately. The characteristic of interview sentence is different from the anchor's and the reporter's in one thing or another. Therefore it disturbs the anchor and reporter oriented language modeling. In this paper, we evaluate the effect of interview sentences in language model for Korean broadcast news transcription system and analyze statistically the relationship between size and balance of text corpus by making an experiment as the same procedure according to varying the size of corpus.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 추계학술발표대회
• /
• pp.339-342
• /
• 2012

Nowadays, Spoken Dialogue System is rapidly growing by investing a lot from researches as well as organizations. One of concrete evidences is that the appearance of commercial systems such as Siri, SVoice, DARPA, CLASSiC, GSearch etc. Moreover, Spoken Dialogue System is widely believed to be the future direction of software development. In Spoken Dialogue System, users interact to software by using their own voice instead of use their hands, keyboard, and mouse. This paper continuously presents our development of the Spoken Dialogue System on News. Particularly, we propose detailed design such as semantic concepts, semantic frames, slots, and so on for applying Hidden Vector State Model into our Spoken Dialogue System for Spoken Language Understanding.