• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.3-14
• /
• 2006

Music summarization means a technique which automatically generates the most importantand representative a part or parts ill music content. The techniques of music summarization have been studied with two categories according to summary characteristics. The first one is that the repeated part is provided as music summary and the second provides the combined segments which consist of segments with different characteristics as music summary in music content In this paper, we propose and evaluate two kinds of music summarization techniques. The algorithm using multi-level vector quantization which provides a repeated part as music summary gives fixed-length music summary is evaluated by overlapping ration between hand-made repeated parts and automatically generated summary. As results, the overlapping ratios of conventional methods are 42.2% and 47.4%, but that of proposed method with fixed-length summary is 67.1%. Optimal length music summary is evaluated by the portion of overlapping between summary and repeated part which is different length according to music content and the result shows that automatically-generated summary expresses more effective part than fixed-length summary with optimal length. The cluster-based algorithm using 2-D similarity matrix and k-means algorithm provides the combined segments as music summary. In order to evaluate this algorithm, we use MOS test consisting of two questions(How many similar segments are in summarized music? How many segments are included in same structure?) and the results show good performance.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.47-54
• /
• 2010

Old archived film shows two major defects: line scratch and blobs. In this paper, we present a design and implementation of an automatic video restoration system for line scratches observed in archived film. We use autoregressive (AR) image model because we can make stochastic and specifically autoregressive image generation process with our PAST-PRESENT model and Sampling Pattern. We designed locality maximizing scanning pattern, which can generate nearly stationary time-like series of pixels, which is a strong requirement for a stochastic series to be autoregressive. The sampled pixel series undergoes filtering and model fitting using Durbin-Levinson algorithm before interpolation process. We designed three-stage film restoration system, which includes (1) film acquisition from VHS tapes, (2) simple line scratch detection and restoration, and (3) manual blob identification and sophisticated inpainting scheme. We implemented film acquisition and simple inpainting scheme on Texas Instruments DSP board TMS320DM642 EVM, and implemented our AR inpainting scheme on PC for sophisticated restoration. We experimented our scheme with two old Korean films: "Viva Freedom" and "Robot Tae-Kwon-V", and the experimental results show that our scheme improves Bertalmio's scheme for subjective quality (MOS), objective quality (PSNR), and especially restoration ratio (RR), which reflects how much similar to the manual inpainting results.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.591-596
• /
• 2022

Various COVID-19 quarantine guidelines and measures are being taken by country at the WHO, but the number of confirmed cases has not decreased significantly. In order to prevent the inflow and outflow of COVID-19 through individual droplets, it is mandatory to wear a mask anytime, anywhere. However, as virus bacteria entering the mask amplify, it pollutes the mask and causes a disgusting smell. In this paper, a new method of preventing the spread of COVID-19 was proposed by sterilizing the mask with a dental gait spray introduced into the mask that has been used for a long time. Dental gargle water is usually produced by electrolysis of tap water, and the unstable ion water (HOCl) dissolved in water penetrates the cell barrier of various viruses and fails to act in its nucleus, causing water to self-purify. As a result of the experiment, when the mask used for a long time was washed with gargle water spray, the washed mask was dried after 10 minutes, and the smell of virus droplets or saliva almost disappeared. In particular, as a result of MOS testing the fit of the subjects who participated in the mask cleaning, it was excellent at 4.4 on average. Therefore, the mask was disposable, but if the spray was washed in the proposed method more than twice a day, the mask could be used in a comfortable state for more than a week.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.422-429
• /
• 2022

A light sensor chip requires a small capacity eFuse (electrical fuse) OTP (One-Time Programmable) memory IP (Intellectual Property) to trim analog circuits or set initial values of digital registers. In this paper, 128-bit eFuse OTP IP is designed using only 3.3V MV (Medium Voltage) devices without using 1.8V LV (Low-Voltage) logic devices. The eFuse OTP IP designed with 3.3V single MOS devices can reduce a total process cost of three masks which are the gate oxide mask of a 1.8V LV device and the LDD implant masks of NMOS and PMOS. And since the 1.8V voltage regulator circuit is not required, the size of the illuminance sensor chip can be reduced. In addition, in order to reduce the number of package pins of the illumination sensor chip, the VPGM voltage, which is a program voltage, is applied through the VPGM pad during wafer test, and the VDD voltage is applied through the PMOS power switching circuit after packaging, so that the number of package pins can be reduced.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.155-163
• /
• 2009

In text-to-speech systems, the conversion of text into prosodic parameters is necessarily composed of three steps. These are the placement of prosodic boundaries. the determination of segmental durations, and the specification of fundamental frequency contours. Prosodic boundaries. as the most important and basic parameter. affect the estimation of durations and fundamental frequency. Break prediction is an important step in text-to-speech systems as break indices (BIs) have a great influence on how to correctly represent prosodic phrase boundaries, However. an accurate prediction is difficult since BIs are often chosen according to the meaning of a sentence or the reading style of the speaker. In Japanese, the prediction of an accentual phrase boundary (APB) and major phrase boundary (MPB) is particularly difficult. Thus, this paper presents a method to complement the prediction errors of an APB and MPB. First, we define a subtle BI in which it is difficult to decide between an APB and MPB clearly as a variable break (VB), and an explicit BI as a fixed break (FB). The VB is chosen using the classification and regression tree, and multiple prosodic targets in relation to the pith and duration are then generated. Finally. unit-selection is conducted using multiple prosodic targets. In the MOS test result. the original speech scored a 4,99. while proposed method scored a 4.25 and conventional method scored a 4.01. The experimental results show that the proposed method improves the naturalness of synthesized speech.