• Korean Linguistics
• /
• v.64
• /
• pp.195-223
• /
• 2014

The aim of this paper is to study the morphemization of {Geuraegajigo} based on a spontaneous speech corpus. For this purpose, the distributions, the semantic functions, and the intonational phrase pattterns of the connective {Geuraegajigo} have been analyzed based on the corpus. The results are as follow; at first, coalescence that comes with a morphemization process was found, resulting in many variations. Secondly, there are three functions of it: [Direct/Indirect interrelationship], [Enumerate conjunction], and [Discourse marker]. And this semantic/functional diversity has many similarities with conjunctive adverbs. Lastly, intonational phrase patterns of {Geuraegajigo} accord with those of conjunctive adverbs. Especially, the discourse strategic IP pattern is connected with the short variation type. In conclusion, {Geuraegajigo} has finished turning into a conjunctive adverb through morphemization.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.272-274
• /
• 2022

최근에는 사람과 기계가 자유롭게 대화를 주고받을 수 있는 자유 주제 대화 시스템(Open-domain Dialogue System)이 다양한 서비스에 활용되고 있다. 자유 주제 대화 시스템이 더욱 다양한 답변을 제공할 수 있도록 사전학습 기반의 생성 언어모델이 활용되고 있지만, 답변 제공의 안정성이 떨어져 검색을 활용한 방법 또한 함께 활용되고 있다. 검색 기반 방법은 사용자의 대화가 들어오면 사전에 구축된 데이터베이스에서 유사한 대화를 검색하고 준비되어있는 답변을 제공하는 기술이다. 하지만 멀티턴으로 이루어진 대화는 일반적인 문서의 문장과 다르게 각 문장에 대한 발화의 주체가 변경되기 때문에 연속된 발화 문장이 문맥적으로 밀접하게 연결되지 않는 경우가 있다. 본 논문에서는 이와 같은 대화의 특징을 고려하여 멀티턴 대화를 효율적으로 임베딩 할 수 있는 DBERT(DialogueBERT) 모델을 제안한다. 기존 공개된 사전학습 언어모델 기반의 문장 임베딩 모델과 비교 평가 실험을 통해 제안하는 방법의 우수성을 입증한다.

• Proceedings of the KSPS conference
• /
• 2006.11a
• /
• pp.19-23
• /
• 2006

This paper is for the comparison of prosodic phrasing in Korean spontaneous speech and read speech. For this comparison, The subjects read the transcriptions from their own spontaneous speech. The number of IP in spontaneous speech is more than in read speech, while The number of AP has no difference between them. A accentual phrase in spontaneous speech has less syllable than read speech.

• Phonetics and Speech Sciences
• /
• v.11 no.2
• /
• pp.33-44
• /
• 2019

This paper dealt with how realization of pauses in utterance is affected by speech style, gender, and generation. For this purpose, we analyzed the frequency and duration of pauses. Pauses were categorized into four types: pause with breath, pause with no breath, utterance medial pause, and utterance final pause. Forty-eight subjects living in Seoul were chosen from the Korean Standard Speech Database. All subjects engaged in reading and spontaneous speech, through which we could also compare the realization between the two speech styles. The results showed that utterance final pauses had longer durations than utterance medial pauses. It means that utterance final pause has a function that signals the end of an utterance to the audience. For difference between tasks, spontaneous speech had longer and more frequent pauses because of cognitive reasons. With regard to gender variables, women produced shorter and less frequent pauses. For male speakers, the duration of pauses with breath was significantly longer. Finally, for generation variable, older speakers produced more frequent pauses. In addition, the results showed several interaction effects. Male speakers produced longer pauses, but this gender effect was more prominent at the utterance final position.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.365-370
• /
• 2023

This paper aims to compare the performance of speech data classification into two groups, adult and elderly, based on the acoustic and linguistic characteristics that change due to aging, such as changes in respiratory patterns, phonation, pitch, frequency, and language expression ability. For acoustic features we used attributes related to the frequency, amplitude, and spectrum of speech voices. As for linguistic features, we extracted hidden state vector representations containing contextual information from the transcription of speech utterances using KoBERT, a Korean pre-trained language model that has shown excellent performance in natural language processing tasks. The classification performance of each model trained based on acoustic and linguistic features was evaluated, and the F1 scores of each model for the two classes, adult and elderly, were examined after address the class imbalance problem by down-sampling. The experimental results showed that using linguistic features provided better performance for classifying adult and elderly than using acoustic features, and even when the class proportions were equal, the classification performance for adult was higher than that for elderly.

• Journal of Korean language education
• /
• v.29 no.3
• /
• pp.345-363
• /
• 2018

The purpose of this study is to compare the speech rate of advanced Korean(L2) learners and Korean native speakers in spontaneous utterances. Specifically, the current study investigated the difference of the two groups' speech pattern according to utterance length. Eight advanced Korean(L2) learners and eight Korean native speakers participated in this study. The data were collected by recording their conversation and physical measurements (speaking rate, articulatory rates, pause and several types of speech disfluency) were taken on extracted 120 utterances from 12 out of the 16 participants. The findings show that advanced Korean learners' speech pattern is similar to that of Koreans in the short-length utterance. However, in the long-length utterance, two groups show different speech patterns; while the articulatory rate of Korean native speakers increased in the long-length utterance, that of Korean learners decreased. This suggests that the frequency of speech disfluency factors might affect this result.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2113-2123
• /
• 1999

The partial free order feature of Korean makes grammar size represented by CFG too big and that's why grammar has to contain all the ordered words. There are some problems to parse spoken language, because spontaneous spoken language has special features such as meaningless words, repetitious speech, etc. So, in this paper, we define 'Core-Concept' as the necessary element for parsing and we describe grammar only using Core-Concept. And we can prevent grammar from becoming very large and reduce an additional parsing burden as we select. Core-Concept described in grammar as parsing element. Through this strategy, we present that the simplified grammar can give us more efficient method to get right results. Experiments show that our parsing strategy has an average of 98% or over success rate in correct parsing results.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.433-438
• /
• 2021

대화 시스템은 크게 사용자와 시스템이 특정 목적 혹은 자유 주제에 대해 대화를 진행하는 것으로 구분된다. 최근 자유주제 대화 시스템(Open-Domain Dialogue System)에 대한 연구가 활발히 진행됨에 따라 자유 주제를 기반으로 하는 상담 대화, 일상 대화 시스템의 독성 발화 제어 생성에 대한 연구의 중요성이 더욱 커지고 있다. 이에 본 논문에서는 대화 모델의 독성 응답 생성을 제어하기 위해 일상 대화 데이터셋으로 학습된 BART 모델에 Plug-and-Play Language Model 방법을 적용한다. 공개된 독성 대화 분류 데이터셋으로 학습된 독성 응답 분류기를 PPLM의 어트리뷰트(Attribute) 모델로 활용하여 대화 모델의 독성 응답 생성을 감소시키고 그 차이를 실험을 통해 정량적으로 비교한다. 실험 결과 어트리뷰트 모델을 활용한 모든 실험에서 독성 응답 생성이 감소함을 확인하였다.

• Korean Journal of Cognitive Science
• /
• v.9 no.1
• /
• pp.41-46
• /
• 1998

The argument-structure distributions of predicates in the speech of two roca-type aphasic patients and one Conduction-type patient are compared with both matched controls and each other on the basis of narrative production data. Whereas English-speaking agrammatics have been reported to have difficulties producing noncopular unaccusative predicates (Kegl 1995) Korean-speaking agrammatics are found not to have particular difficulties with unaccusative predicates. On the assumption that agrammatics lack specific syntactic knowledge for the processing of displaced arguments from their lexically specified positions. it is proposed that unaccusatives in Korean do not involve the displacement of arguments for Case-theoretic reasons or involve a vacuous movement. if any.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.137-140
• /
• 2003

본 연구는 치매노인환자의 생활의 질을 향상시키기 위한 대화시스템의 개발에 목표를 둔다. 제안된 시스템은 주로 세 가지 모듈, 즉, 음성인식, 시간테이블에 의해 구분된 대화 데이터베이스의 자동검색, 그리고 간호사의 녹음음성에 의한 응답 등으로 구성되어 있다. 우선 치매환자가 요양시설에서 자주 발화하는 대화의 내용을 조사하고, 그들의 발화 음성을 인식하고 적절히 응답하도록 구성하였다. 시스템의 평가를 위해서 시스템이 도입되었을 때와 도입되지 않았을 때를 비교, 조사하였다. 시스템이 도입되지 않았을 때는 간호사가 자유로이 케어서비스를 행할 수 있도록 하였다. 비디오 촬영을 통해서 대상자의 행동 및 반응을 조사한 결과, 치매환자의 요구를 충족시키는데 있어서 대화 시스템이 간호사들보다 더 응답적이었다는 것을 알 수 있었다. 게다가, 제안된 시스템은 상호 대화에 있어서 환자가 더 많이 말하도록 유도함을 알 수 있었다.