• Speech Sciences
• /
• v.12 no.3
• /
• pp.105-114
• /
• 2005

It was verified that a speaker verification system improved its performances of EER by regularizing log likelihood ratio, using background speaker models. Recently the wireless mobile phones are becoming more dominant communication terminals than wired phones. So the need for building a speaker verification system on mobile phone is increasing abruptly. Therefore in this paper, we had some experiments to examine the performance of speaker verification based on mobile phone's voices. Especially we are focused on the performance variations in EER(Equal Error Rate) according to several background speaker's characteristics, such as selecting methods(MSC, MIX), number of background speakers, aging factor of speech database. For this, we constructed a speaker verification system that uses GMM(Gaussin Mixture Model) and found that the MIX method is generally superior to another method by about 1.0% EER. In aspect of number of background speakers, EER is decreasing in proportion to the background speakers populations. As the number is increasing as 6, 10 and 16, the EERs are recorded as 13.0%, 12.2%, and 11.6%. An unexpected results are happened in aging effects of the speech database on the performance. EERs are measured as 4%, 12% and 19% for each seasonally recorded databases from session 1 to session 3, respectively, where duration gap between sessions is set by 3 months. Although seasons speech database has 10 speakers and 10 sentences per each, which gives less statistical confidence to results, we confirmed that enrolled speaker models in speaker verification system should be regularly updated using the ongoing claimant's utterances.

• Journal of Korean Society of Rural Planning
• /
• v.25 no.1
• /
• pp.21-38
• /
• 2019

Korean agricultural industry has weakened as demand for domestic agricultural products has declined due to accelerating market liberalization, aging and shrinking of rural population, and stagnating rural households' incomes. On the other hand, as the forth industrial revolution unfolds in earnest, tremendous changes are expected, and those changes won't be confined to certain industries but would shaken the world we know of entirely. Smart farm, which is one example of the fourth industrial revolution, is increasingly being recognized as a new growth engine for the future as smart farm and the science and technology behind it, not the size of arable land, will determine competitiveness of the agricultural industry and drive agricultural productivity and managerial efficiency. In consideration that John W. Kingdon's Multiple Streams Framework has recently been presented as an important theoretical model in the policy field, this study analyzed problem stream, policy stream, and political stream in the process of forming the smart farm policy, and looked into what role the government played as policy entrepreneur in policy window. The smart farm policy was put on policy agenda by the government and was approved when the government announced the Smart Farm Plan together with relevant ministries at the 5th Economy-Related Ministers' Meeting held in April 2018. This suggests that change of the government is the most critical factor in political stream, and explicitly indicates the importance of politics in formation of an agricultural policy. In addition, actual outcome of the policy and how policy alternatives that will enhance people's understanding will support it seem to be the key to success. It also shows that it is important that policy alternatives be determined based on sufficient discussion amongst stakeholders.