• Annual Conference on Human and Language Technology
• /
• 2003.10d
• /
• pp.241-245
• /
• 2003

본 논문은 기계번역 시스템의 성능평가를 위한 '핵심어 전달율 측정' 방안에 대해서 기술한다. 기계번역 시스템의 성능평가는 두 가지 측면으로 고려될 수 있다. 첫 번째는 객관적인 평가로 IBM에서 주창한 BLEU score 측정이나 NIST의 NIST score 측정이 그 예이다. 객관적인 평가는 평가자의 주관적인 판단이나 언어적인 특성을 배제한 방법으로 프로그램을 통해 자동으로 fluency와 adequacy를 측정하여 성능을 평가한다. 다음은 주관적인 평가이다. 주관적인 평가는 평가자의 평가를 통해 번역의 품질을 평가하는 방법이다. 주관적 평가 방법의 대표적인 것으로는 NESPOLE이나 LDC가 있다. 주관적인 평가는 평가자의 정확한 판단으로 신뢰할만한 성능평가 결과를 도출하지만, 시간과 비용이 많이 들고, 재사용할 수 없다는 단점이 있다. 본 논문에서는 이러한 문제를 해결하기 위해, 번역대상 문장에서 핵심어를 추출하고, 그 핵심어가 기계번역 시스템의 수행결과에 전달된 정도를 자동으로 측정하는 새로운 평가방법인 '핵심어 전달율 측정' 방안을 제안한다. 이는 성능평가의 비용과 시간을 절약하고, 주관적 평가와 유사한 신뢰성 있는 평가결과를 얻을 수 있는 좋은 지표가 될 수 있을 것으로 기대한다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.2
• /
• pp.102-108
• /
• 1999

It is important to decide processing unit in the large vocabulary speech recognition system we propose a Pseudo-Morpheme as the recognition unit to resolve the problems in the recognition systems using the phrase or the general morpheme. We implement a morphological analysis system and tagger for Pseudo-Morpheme. The speech processing system using this pseudo-morpheme can get better result than other systems using the phrase or the general morpheme. So, the quality of the whole spoken language translation system can be improved. The analysis-ratio of our implemented system is similar to the common morphological analysis systems.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.552-554
• /
• 2019

Deaf mutism (a hearing-impaired person and speech disorders) communicates using sign language. There are difficulties in communicating by voice. However, sign language can only be limited in communicating with people who know sign language because everyone doesn't use sign language when they communicate. In this paper, a finger language translation system is proposed and implemented as a means for the disabled and the non-disabled to communicate without difficulty. The proposed algorithm recognizes the finger language data by leap motion and self-learns the data using machine learning technology to increase recognition rate. We show performance improvement from the simulation results.

• The Journal of Korean Physical Therapy
• /
• v.31 no.2
• /
• pp.88-93
• /
• 2019

Purpose: The aim of the study was to develop a Korean version of an ICF e-Learning tool (KICF e-Learning tool). Methods: The process of translation and adaptation of the ICF e-Learning tool was followed: two translators developed the Korean versions independently, and a consensus version of the translation was then produced. An expert committee, which was composed of five experts from physiotherapy, occupational therapy, speech pathology, and social welfare, reviewed the consensus Korean version to make a beta version of the tool. A field test was conducted to determine if the Korean version of the tool was easy to understand and suitable to use in ICF learning. Feedback from the field test were used for the final adaptation of the KICF e-Learning tool. Results: One-hundred and twenty-six volunteers (40 males and 76 females) were invited to examine the KICF e-Learning tool. The participants reported various levels of ICF knowledge from none to very good. Forty-eight participants reported no knowledge of ICF. The majority of participants (n=84) reported that Korean terms or expression in the tool were easy to understand and one-hundred fourteen participants would recommend the tool to another person. The Korean cases would be helpful for a Korean audience to study the ICF using the tool. Conclusion: The KICF e-Learning tool was developed and is ready for use by the public for the consistency of ICF education. On the other hand, development of an advanced module will be needed.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.271-276
• /
• 1997

대화체는 문어체와는 달리 화자와 청자 사이의 질의/응답으로 이루어진 형태의 문장들을 가지며, 생략과 대용어가 빈번히 발생하는 특징을 갖는다. 이러한 대화 형태에서 어떠한 한 문장에는 화자가 전달하고자 하는 의도를 포함하고 있다. 이러한 대화체 문장들을 번역하는 것은 단순한 언어적 분석에 의한 번역으로서는 많은 번역상의 오류가 발생하게 된다. 따라서 대화체 문장들의 올바른 번역을 위해서는 대화의 상황을 반영하는 문맥 정보가 부가적으로 요구된다. 본 연구에서는 이러한 문맥 정보로서 화행을 사용하여 대화체 기계번역을 수행하고자 한다. 화행(Speech Act)이란 화자에 의해 의도되어 발화 속에 포함된 언어적 행위를 나타내며, 이러한 화행을 분석함으로써 화자의 의도를 파악하고 이를 통해 올바른 번역을 수행할 수 있게 된다. 본 기계번역 시스템에 포함된 화행 분석 과정에서는 대화를 화행으로 모델링한 담화 문법과 유사한 형태의 재귀적 대화 전이망(Recursive Dialog Transition Network)을 사용하게 된다. 본 논문에서는 호텔 예약 영역에서의 기계번역 시스템에 대한 간단한 소개와 화행의 종류 및 분석 방법과 이를 통한 기계번역 방식에 대해 살펴보도록 하겠다.

• Speech Sciences
• /
• v.14 no.1
• /
• pp.7-19
• /
• 2007

The present study investigates the so-called frequency inheritance effect in word production. According to some earlier studies (e.g. Jescheniak & Levelt, 1994), retrieval of a low-frequency homophone benefits from its high-frequency homophone twin, and more specifically word-retrieval RT is determined by the frequency of the phonological form of the word (sum of homophone frequencies) rather than the frequency of the specific word. This result, however, has been challenged by later studies (e.g. Caramazza et al., 2001) and one possible resolution is that languages differ in the extent to which the inheritance effect occurs. Two experiments are reported to test whether the frequency inheritance effect depends on the target language, namely, if a language such as Korean with relatively many homophones tend not to show frequency inheritance, which is compared with the language with fewer homophones such as Dutch and German (Jescheniak & Levelt, 1994; Jescheniak et al., 2003). Experiment 1 was picture naming, and Experiment 2 used an English-to-Korean translation task. In both experiments, the homophones were actually slower than the low-frequency controls, suggesting that there was no evidence for the inheritance effect. These results imply that the issue of whether specific word or homophone frequency determines production can be properly assessed by taking into account the language-specific nature of the lexicon such as the percentage of the homophone words in that language.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.4
• /
• pp.321-327
• /
• 2015

In this paper, we propose an algorithm for achieving robust Visual Voice Activity Detection (VVAD) for enhanced speech recognition. In conventional VVAD algorithms, the motion of lip region is found by applying an optical flow or Chaos inspired measures for detecting visual speech frames. The optical flow-based VVAD is difficult to be adopted to driving scenarios due to its computational complexity. While invariant to illumination changes, Chaos theory based VVAD method is sensitive to motion translations caused by driver's head movements. The proposed Local Variance Histogram (LVH) is robust to the pixel intensity changes from both illumination change and translation change. Hence, for improved performance in environmental changes, we adopt the novel threshold estimation using total variance change. In the experimental results, the proposed VVAD algorithm achieves robustness in various driving situations.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.6 s.312
• /
• pp.43-51
• /
• 2006

This paper proposes a metrics for example matching under the example-based machine translation for English-Korean machine translation. Our metrics served as similarity measure is based on edit-distance algorithm, and it is employed to retrieve the most similar example sentences to a given query. Basically it makes use of simple information such as lemma and part-of-speech information of typographically mismatched words. Edit-distance algorithm cannot fully reflect the context of matched word units. In other words, only if matched word units are ordered, it is considered that the contribution of full matching context to similarity is identical to that of partial matching context for the sequence of words in which mismatching word units are intervened. To overcome this drawback, we propose the context-weighting scheme that uses the contiguity information of matched word units to catch the full context. To change the edit-distance metrics representing dissimilarity to similarity metrics, to apply this context-weighted metrics to the example matching problem and also to rank by similarity, we normalize it. In addition, we generalize previous methods using some linguistic information to one representative system. In order to verify the correctness of the proposed context-weighted metrics, we carry out the experiment to compare it with generalized previous methods.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.287-290
• /
• 1994

음성 인식 시스템의 개발을 위해서는 음성 데이터베이스구축이 중요한 과제의 하나로서, 많은 시간과 노력이 요구된다. 개별적인 음성데이타베이스 구축에 따른 중복 투자를 줄이고 다양한 인식 알고리듬의 성능 비교와 국내 음성 인식 기술의 발전을 위해서는 벤치마크 시험을 위한 공통의 음성 데이터베이스가 필수적이다. 본 논문에서는 한국과학기술원 통신연구실에서 제작한 한국어 음성 데이터베이스에 관하여 기술한다. KAIST 음성데이타베이스는 자동통ㅇ역을 N이한 무역 상담과 관련되 3,000 단어 규모의 연속어를 비롯하여, 가변 길이 연결 숫자음, phoneme-balanced 75 고립단어, 지역명 관련 500 고립단어, 한국어 아-세트로 구성되어 있다. 이 음성 데이터베이스의 구축을 위하여 사용된 태스크선정 절차, 녹음 방법, 규격, 및 기대효과 등 세부사항을 기술한다.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.187-192
• /
• 2007

The purpose of this paper is to show that the current notation of Japanese proper names in Korean has some problems. It cannot represent the different sounds between the voiced and voiceless. The purpose of this paper is also to give a more correct notation which is coherent and efficient. After introducing some general knowledge about the phonemes of Japanese language, I measured the Voice Onset Time of the stops[k, t] at the beginning, in the middle and at the end of a word, and compared the spectrogram of affricates with that of fricatives. In conclusion, Japanese voiceless [k, t ,$t{\int}$] should be written as [ㅋ,ㅌ,ㅊ] and voiced [g, d $d_3$] as [ㄱ,ㄷ,ㅈ] and the affricate[ts] as[ㅊ] in Korean.