Seok-Pil Lee

Learn More
— The robustness of audio fingerprinting system in a noisy environment is a principal challenge in the area of content-based music retrieval, especially for use in portable consumer devices. Our new audio fingerprint method using sub-fingerprint masking based on the predominant pitch extraction dramatically increases the accuracy of the audio fingerprinting(More)
It has become general that consumers freely create contents and spend them for themselves on Web services in Web 2.0 environments. This research introduces the personalized contents recommendation system that answers the recent propensity trends about the multimedia contents based on web environments. The proposed system mined the usage history patterns of(More)
Compared with conventional full-band speaker recognition systems, Advanced Missing Feature Theory (AMFT) produces a much lower error rate, but requires increased computational complexity. We propose a weighting function for the score calculation algorithm in AMFT. The weighting function is estimated by calculating the number of reliable spectral components.(More)
In H.264 video compression standard, B frame bi-directional predictions and its DIRECT mode coding are included to enhance video compression efficiency. However, such tools require a complex mode decision process and result in a long computation time. Therefore, fast algorithms are crucial in implementing H.264. In this paper, to save B frame encoding time,(More)
In spite of the progress made in the past decade, the quality-of-services (QoS) of the video-conferencing (VC) systems involving four or more sites need to be improved much further in order to attract a large number of users. One of the key issues in enabling high-level QoS in multi-party (MP) VC systems is the accurate maintenance of the temporal(More)