Hee-Ae Ko

Speaker Verification System Using Extended Sequential Probability Ratio Test in PDA

We propose a speaker-verification (SV) system to protect personal information stored on personal digital assistant (PDA) devices. PDAs have recently increased in capability and have increased in popularity, especially among highly mobile consumers. However, there still exist numerous obstacles to the practical use of SV with PDA devices because SV requires high computational complexity. To solve this problem, we propose a method to improve SV performance by applying the extended sequential probability ratio test (ESPRT) to the decision logic threshold. The proposed system is compatible with a PDA devices limited memory and low CPU speed.

A Scheme that Transcodes and Services from PC Web Page to Mobile Web Page of Dynamic Object with DOM

With development of mobile communications terminal and expansion of mobile Internet, a large number of users can use mobile web contents at anytime and anywhere and will demand service of greater contents. Due to such demand, many studies are being carried out on transcoding contents so that wired web contents can be used in mobile web. However, transcoding and creation of mobile web contents involve difficulties because specifications available from telecommunications companies and mobile terminals have not been standardized. Especially, in order for serving dynamic object of wired web page contents to dynamically change according to time or user, it is required not only to program scripts to suit each terminal, but also to transcode the resources used in advance. for solution to this problem, this study uses the hierarchy structure of DOM (document object model) to display structural characteristics of wired web page. In other words, this study proposes the following technique. Wired web pages are analyzed and the results are established as data structure. Then, dynamic object is extracted and the domain is indexed so that, when serving mobile web page, information can be extracted at the indexed position to create mobile web contents for service on real-time basis. Also, this study aims at developing an editing device to edit mobile web contents and mobile web service server to service the edited contents by applying the above technique.

Research on WINC expansion numbers to improve the accessibility of mobile web service

For the past few years, unlike wireless widespread United States and Japan, expensive cost and platform of the mobile web carrier underground and self-centered made achievement of domestic mobile web market sluggish. Nowadays, more and more people pay attention to the mobile web service because of the increased quality of wireless internet, development of mobile device and variety of the flat-rate payment system. However, another big problem is that mobile web is too hard to use. Also, the poor content of mobile web service is an extremely serious problem. In this paper, we put forward a new method for easy to access mobile web service which is use WINC expansion numbers and users can use these numbers to shit their own website. Along with the benefits of purchase WINC number general users are able to make website and control their website at less time and energy.

Composition Technique for Independent Real-time Advertisement on Mobile UCC Phonepage

One of the advantages of the mobile internet is that it is accessible everywhere. However, producing the mobile internet contents is hard because the standards of the contents are different depending on the telecommunications companies and the mobile phone terminals. Because of this, mobile contents production has not been activated and profit models are rarely found. In order to vitalize the mobile contents, we developed the Mobile UCC (User Created Contents) Phone Page Service with which general users can produce and provide the mobile phone pages easily. In addition, we began to provide advertisement on the UCC phone pages as a profit model. However, as mentioned already, the contents that meet each of the standards should be prepared in advance to be compatible with the different standards. For this reason, only one advertisement could be provided on one UCC phone page. Previous studies were focused on the standardization of different standards by integrating them. Though the standardization may be applicable to the mobile phones that will be newly released, it is hardly applied to the conventional mobile phones. To solve the abovementioned problems and improve the drawbacks of the conventional studies, we proposed in this article the technology to synthesize the phone page contents and independent advertisement at the moment when the UCC phone page prepared by the users is provided in real time. This technology allows to provide various advertisement on one UCC phone page and administrate the start, end and frequency of specific advertisements. This method was applied in this study to vitalize the mobile contents and improve the profit model.

A global covariance matrix based principal component analysis for speaker identification

Principal component analysis (PCA) is an efficient feature extraction method which reduces the dimensions of the feature vectors and removes the correlation among them, with little loss of information, by projecting the original feature space into a small subspace through a transformation. However, it requires a larger amount of training data when calculate the full covariance matrix of each speaker. This paper proposes an efficient global covariance matrix-based PCA for speaker identification. The proposed method uses training data from all speakers to calculate the global covariance matrix and then uses this matrix to find the eigenvalue matrix and the eigenvector matrix to perform PCA. During training and testing, our method uses PCA coefficients that are based on global covariance instead of the PCA coefficients of each speaker. Compared to the conventional PCA and the Gaussian mixture model (GMM) methods, the proposed method shows better performance while requiring less storage space and complexity.