• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.8
• /
• pp.1625-1631
• /
• 2005

This paper describes an optimization of a language model and an acoustic model that improve the ability of speech recognition with Korean nit digit. Recognition errors of the language model are decreasing by analysis of the grammatical feature of korean unit digits, and then is made up of fsn-node with a disyllable. Acoustic model make use of demi-syllable pair to decrease recognition errors by inaccuracy division of a phone, a syllable because of a monosyllable, a short pronunciation and an articulation. we have used the k-means clustering algorithm with the transformed successive state splining in feature level for the efficient modelling of the feature of recognition unit . As a result of experimentations, $10.5\%$ recognition rate is raised in the case of the proposed language model. The demi-syllable pair with an acoustic model increased $12.5\%$ recognition rate and $1.5\%$ recognition rate is improved in transformed successive state splitting.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.448-453
• /
• 2023

대규모 언어 모델 (Large Language Model, LLM)을 인간의 선호도 관점에서 평가하는 것은 기존의 벤치마크 평가와는 다른 도전적인 과제이다. 이를 위해, 기존 연구들은 강력한 LLM을 평가자로 사용하여 접근하였지만, 높은 비용 문제가 부각되었다. 또한, 평가자로서 LLM이 사용하는 주관적인 점수 기준은 모호하여 평가 결과의 신뢰성을 저해하며, 단일 모델에 의한 평가 결과는 편향될 가능성이 있다. 본 논문에서는 엄격한 기준을 활용하여 편향되지 않은 평가를 수행할 수 있는 평가 프레임워크 및 평가자 모델 'FubaoLM'을 제안한다. 우리의 평가 프레임워크는 심층적인 평가 기준을 통해 다수의 강력한 한국어 LLM을 활용하여 연쇄적 사고(Chain-of-Thought) 기반 평가를 수행한다. 이러한 평가 결과를 다수결로 통합하여 편향되지 않은 평가 결과를 도출하며, 지시 조정 (instruction tuning)을 통해 FubaoLM은 다수의 LLM으로 부터 평가 지식을 증류받는다. 더 나아가 본 논문에서는 전문가 기반 평가 데이터셋을 구축하여 FubaoLM 효과성을 입증한다. 우리의 실험에서 앙상블된 FubaoLM은 GPT-3.5 대비 16% 에서 23% 향상된 절대 평가 성능을 가지며, 이항 평가에서 인간과 유사한 선호도 평가 결과를 도출한다. 이를 통해 FubaoLM은 비교적 적은 비용으로도 높은 신뢰성을 유지하며, 편향되지 않은 평가를 수행할 수 있음을 보인다.

• Journal of Korea Technology Innovation Society
• /
• v.21 no.4
• /
• pp.1296-1312
• /
• 2018

The wave of the Fourth Industrial Revolution was spreaded in Moon Jae-in Government. The efficiency of the R&D budget of government began to pay attention, the role of the National Science & Technology Information Service (NTIS) which provides all national R&D information in real time World's first R&D information portal has been emphasized. NTIS provides information on national R&D projects with their participating researchers, outcomes, and facilities & equipment through of information from each ministry and institution. NTIS supports to build science and technology policies, to enable transparent and efficient management of national R&D projects and to promote joint utilization of the R&D data among researchers and industrial utilization of the R&D data. NTIS provides since 2005. In this paper, I have analyzed the economic ripple effect of NTIS using the Input-Output model technique based on the input-output tables published by the Bank of Korea. When I set the NTIS R&D budget (about 120M$ for the last 13 years) as input coefficients, the effect on production inducement, value added inducement and employment inducement was analyzed by 211M$, 100M$ and 1,882 respectively.

• Journal of Cadastre & Land InformatiX
• /
• v.54 no.1
• /
• pp.33-48
• /
• 2024

This study aims to establish the scope and statistics of the K-address information industry in Korea, estimating its size and prospects and estimates the economic effects through K-address information industry based on Input-Output analysis. Considering the characteristics and sectoral structure of the K-address information industry, the study delineates the scope and specific sectors, constructing sectoral statistics linked to the KSIC and the Bank of Korea's industrial classification. The study estimates the sectoral industry size, taking into account potential markets. Furthermore, it analyzes the economic impact of each sector within the K-address information industry. To figure out the economic effects, the study conducts Input-Output analysis by setting the K-address information industry as an exogenous sector in the input-output table. The results indicate that the overall size of the K-address information industry is estimated to grow from 406.1 billion KRW in 2021 to 3.65 trillion KRW in 2030. The economic effects of the K-address information industry vary by sector, emphasizing the importance of synergies and integration with related sectors, particularly those with significant inducement effects in high value-added manufacturing and service sectors. Furthermore, the industry's sensitivity to economic fluctuations is evident through the input-output analysis of inter-industry chain effects.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.216-230
• /
• 2018

In this paper, we analyze the economic ripple effects of technology related to the unmanned aerial vehicle industry by applying industry association analysis. Specifically, the effects of employment creation, value added inducement, sensitivity coefficient, and influence coefficient can be calculated, and implications for the analysis result are presented. As a result, the employment inducement effect was confirmed to be 10.017 persons per 1 billion won of investment. The value added inducement effect was much higher than the other manufacturing industry average (employment inducement coefficient: 2.285, value added inducement coefficient: 0.581) when the 1 won budget was added, resulting in 0.9771 won added value. In the unmanned aerial vehicle industry, the coefficient of sensitivity, which means the front chain effect, is 0.7870, which is lower than the manufacturing average (sensitivity coefficient 1.125), and the coefficient of influence, which means the backward chain effect, is 1.161, which is higher than the manufacturing average (influence coefficient: 1.116). Therefore, it is classified as the final demand manufacturing industry. This means that the unmanned aerial vehicle industry is an industry that is less affected by economic fluctuations and can be interpreted as an industry with a greater economic impact than other sectors. Based on these data, it can be used to establish the R&D investment direction policy of the unmanned aerospace industry.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.11
• /
• pp.340-347
• /
• 2016

Since the 1970s, manufacturing has been one of the key driving forces that has led to Korea's economic growth. However, this growth rate has been reduced significantly since the 2000s, and shows that revenues and employment are steadily decreasing. In addition, while manufacturing investment in Korea has dropped sharply, the United States, Germany, Japan, and other major countries have increased investment in manufacturing. These countries have promoted manufacturing innovation strategies that include the convergence of information and communications technologies (ICT) and manufacturing. For manufacturing innovation, it is important for time and cost savings required for product development to be achieved by changes in the production process, especially product design. Modeling and simulation (M&S) is a process that replaces physical product design, mockup making, and testing, with virtual product creation (modeling) and engineering analysis (simulation). In this paper, we analyze the economic ripple effect of supercomputing M&S using an input-output model technique based on the input-output tables published by the Bank of Korea. When we set the M&S budget (about US$16 million for the last 10 years) of the Korea Institute of Science and Technology Information (KISTI) as input coefficients, the effect on production inducement, value-added inducement, and employment inducement was analyzed to be US$24 million, US$13.4 million, and 267, respectively.

• Journal of Technology Innovation
• /
• v.28 no.4
• /
• pp.97-126
• /
• 2020

This study evaluated its potentials by quantitatively analyzing the national economic impact of the smart home-related industry, which is attracting attention as a core industry of the 4th industrial revolution. For the analysis, the smart home-related industries were classified into manufacturing and service industries through a literature review of the previous studies. Using the 2018 input-output table, this paper analyzed linkage effects between industries as well as spillover effects in the production, value-added, employment and job. As a result, the smart home manufacturing and service sectors showed a higher spillover effect in value-added than other industries in each industrial field. In the smart home industry, the spillover effects of manufacturing sector to service sector are larger than those of service sector to manufacturing sector. Moreover, it was confirmed that smart home industry was highly related to not only the technology-intensive industry, but also the service sector for smart cities, smart cars, Fin-tech, and etc. On the other hand, the smart home manufacturing sector is a final demanding industry with relatively higher backward linkage effect than forward linkage effect. In the smart home service sector, the forward linkage effect was relatively high compared with the backward linkage effect, indicating that it was an industry with a high supply function to other industries.

• Convergence Security Journal
• /
• v.4 no.3
• /
• pp.83-90
• /
• 2004

Preventive measures and control over cyber terrorism in Korea is a complex problem. Today laws should meet requirements made by modern technologies development, Law enforcement, special services and judicial system cooperation, their efforts coordination and their material security are priority directions, None of the country is able to prevent cyber terror independently and international cooperation in this field is vital. Taking the above into consideration, we propose and inisit that National Intelligence Service(NIS) should share cyber terror data with Police Agency and have top police authority over the cyber terror.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.13 no.4
• /
• pp.76-91
• /
• 2005

항공운송산업은 여객운송과 화물운송 등에 있어서 그 비중이 계속적으로 증가하여 왔으며 다양한 산업 및 기업들과 연관되어 있다. 그런데 항공운송산업에서 파업이 발생한다면 이를 대체할 만한 수단이 없어 항공사가 막대한 손실을 입을 뿐만 아니라 파업의 연쇄효과로서 적기납품 곤란으로 인한 수출관련 기업에의 타격, 관광 등 연관산업에의 악영향, 기업 및 국가 신인도 하락, 국민생활의 불편과 사회불안 등을 야기시킨다. 이렇듯 항공사 파업에 의한 경제 손실규모가 일반 사업장과는 비교가 안 될 만큼 막대하기에 국가적 차원에서 논의되어야 할 필요가 있다. 현생법상 항공운송산업은 공익사업으로서 노동부장관의 긴급조정 결정으로 노동쟁의를 해결할 수 있게 되어있다. 그러나 긴급조정 제도는 발동요건상 활용에 어려운 점이 많아서 경영계는 직권중재제도의 도입을 주장하고, 노동계는 직권중재 및 일방중재신청제도의 폐지를 주장하고 있으며, 정부는 새로운 대안으로서 최소업무 유지 의무 제도 도입 등을 고려하고 있으나 항공운송산업이 갖는 특수성, 공공성과 국민경제에 미치는 영향을 고려해 볼 때 필수공익사업 지정과 직권중재의 활용이 더 적절한 방법이라고 보여지며, 남용방지를 위해 회부요건·절차 등은 법률로 명시할 필요가 있다. 만일 직권중재제도가 폐지되고 최소업무 유지의무 제도가 도입된다면 항공운송산업이 그 대상업무에 반드시 포함되어야 한다.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.3
• /
• pp.240-246
• /
• 2015

In this paper, speech enhancement using nonnegative matrix factorization with temporal continuity has been addressed. Speech and noise signals are modeled as Possion distributions, and basis vectors and gain vectors of NMF are modeled as Gamma distributions. Temporal continuity of the gain vector is known to be critical to the quality of enhanced speech signals. In this paper, temporal continiuty is implemented by adopting Gamma-Markov chain priors for noise gain vectors during the separation phase. Simulation results show that the Gamma-Markov chain models temporal continuity of noise signals and track changes in noise effectively.