• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.46-63
• /
• 1995

This thesis described an unlimited vocabulary connected speech recognition system using Time Delay Neural Network(TDNN). The recognition unit is the diphone unit which includes the transition section of two phonemes, and the number of diphone unit is 329. The recognition processing of korean connected speech is composed by three part; the feature extraction section of the input speech signal, the diphone recognition processing and post-processing. In the feature extraction section, the extraction of diphone interval in input speech signal is carried and then the feature vectors of 16th filter-bank coefficients are calculated for each frame in the diphone interval. The diphone recognition processing is comprised by the three stage hierachical structure and is carried using 30 Time Delay Neural Networks. particularly, the structure of TDNN is changed so as to increase the recognition rate. The post-processing section, mis-recognized diphone strings are corrected using the probability of phoneme transition and the probability o phoneme confusion and then the eojeols (Korean word or phrase) are formed by combining the recognized diphones.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.6
• /
• pp.1149-1154
• /
• 2017

To obtain good recognition performance of speech recognition system under background noise, it is very important to select appropriate feature parameters of speech. The feature parameter used in this paper is Mel frequency cepstral coefficient (MFCC) with the human auditory characteristics applied to Wiener filter method. That is, the feature parameter proposed in this paper is a new method to extract the parameter of clean speech signal after removing background noise. The proposed method implements the speaker recognition by inputting the proposed modified MFCC feature parameter into a multi-layer perceptron network. In this experiments, the speaker independent recognition experiments were performed using the MFCC feature parameter of the 14th order. The average recognition rates of the speaker independent in the case of the noisy speech added white noise are 94.48%, which is an effective result. Comparing the proposed method with the existing methods, the performance of the proposed speaker recognition is improved by using the modified MFCC feature parameter.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.6 no.2
• /
• pp.95-106
• /
• 2007

This paper proposes an effective tempo feature extraction method for music information retrieval. The tempo information is modeled by the narrow-band temporal modulation components, which are decomposed into a modulation spectrum via joint frequency analysis. In implementation, the tempo feature is directly extracted from the modified discrete cosine transform coefficients, which is the output of partial MP3(MPEG 1 Layer 3) decoder. Then, different features are extracted from the amplitudes of modulation spectrum and applied to different music information retrieval tasks. The logarithmic scale modulation frequency coefficients are employed in automatic music emotion classification and music genre classification. The classification precision in both systems is improved significantly. The bit vectors derived from adaptive modulation spectrum is used in audio fingerprinting task That is proved to be able to achieve high robustness in this application. The experimental results in these tasks validate the effectiveness of the proposed tempo feature.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.2 s.105
• /
• pp.171-177
• /
• 2006

A low-cost, high-performance 40 Gb/s clock recovery module using a phase-locked loop(PLL) for a 40 Gb/s optical receiver with the clock-hold function has been designed and implemented. It consists of a clock extractor circuit, an RF mixer and a frequency discriminator for phase/frequency detection, a VC-DRO, a phase shifter, and a clock-hold circuit. The extracted 40 GHz clock is synchronized with a stable 10 GHz VC-DRO. The clock stability and jitter characteristics of the implemented PLL-based clock recovery module are significantly improved as compared with those of the conventional open-loop type clock recovery module with a DR filter. The measured peak-to-peak RMS jitter is about 230 fs. When an input signal is dropped, the 40 GHz clock is maintained continuously by the hold circuit.

• Journal of Korea Multimedia Society
• /
• v.7 no.9
• /
• pp.1233-1239
• /
• 2004

In a speech coding system using excitation source of voiced and unvoiced, it would be involved a distortion of speech qualify in case coexist with a voiced and an unvoiced consonants in a frame. This paper present a new multi-pulse coding method by using V/S/TSIUVC switching, individual pitch pulses and TSIUVC approximation-synthesis method in order to restrict a distortion of speech quality. The TSIUVC is extracted by using the zero crossing rate and individual pitch pulse. And the TSIUVC extraction rate was 91% for female voice and 96.2% for male voice respectively. The important thing is that the frequency information of 0.347kHz below and 2.813kHz above can be made with high quality synthesis waveform within TSIUVC. I evaluate the MPC use V/UV and the FBD-MPC use V/S/TSIUVC. As a result, I knew that synthesis speech of the FBD-MPC was better in speech quality than synthesis speech of the MPC.

• Journal of Advanced Navigation Technology
• /
• v.18 no.2
• /
• pp.151-157
• /
• 2014

Recently UAV(unmanned aerial vehicle) is frequently used not only for military purpose but also for civil purpose. UAV automatically navigates following the coordinates input in advance using GPS information. However it is impossible when GPS cannot be received because of jamming or external interference. In order to solve this problem, we propose a real-time segmentation and classification algorithm for the specific regions from UAV image in this paper. We use the super-pixels algorithm using graph-based image segmentation as a pre-processing stage for the feature extraction. We choose the most ideal model by analyzing various color models and mixture color models. Also, we use support vector machine for classification, which is one of the machine learning algorithms and can use small quantity of training data. 18 color and texture feature vectors are extracted from the UAV image, then 3 classes of regions; river, vinyl house, rice filed are classified in real-time through training and prediction processes.

• Journal of the Korean Society of Radiology
• /
• v.8 no.2
• /
• pp.65-74
• /
• 2014

This study extracts characteristics of signal by wavelet transform to prove that the Compton scattering, occurred by changed the energy, influenced a picture. We also analyzed the extracted data and evaluated how much the picture of scatter-rays was affected by a change of tube voltage. For this study, we wrote a program with MatLap which is engineering tool and evaluated with the program on variation of scattered-rays due to increased tube voltage. The evaluation result shows both CR and DR have frequency changes of high frequency area by tube voltage variations and it proved that Compton scattering influences the picture. In conclusion, according to this study indicates that DR is more sensitive to radiation with high energy than CR. Therefore, the research on DR detector needs to be advanced as actual condition of clinical setting is being changed to DR circumstance gradually. From the result of this study, we expect that assessment method of the image quality using MatLab Tool becomes the official assessment method and very useful method.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.1
• /
• pp.292-298
• /
• 2018

In this study, Ascidian shell pigment was extracted, first using a 100.0 % ethanol solvent, proceeding with the dilution of it with DMSO (Dimethyl sulfoxide). The extracted pigment was evaluated to verify the stability. The absorbance of light have been evaluated according to pH levels and using the color-difference meter. As a result, it could be seen that absorbance and chromaticity ${\pm}a$ values were most stable at a pH level of 7.0 By keeping the sample at a pH level of 3.0, it could be observed that the absorbance and the chromaticity ${\pm}a$ values were decreased. Based on this observation, it can be deduced that the discoloration of the pigment can be prevented if kept at a neutral pH level. When antioxidants were added, the absorbance of the pigment increased, and the best effects could be seen in the ${\alpha}-tocopherol$ and glutathione samples.

• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.19-26
• /
• 2009

This paper presents an approach to classify normal and ventricular tachycardia/fibrillation(VT/VF) from the Creighton University Ventricular Tachyarrhythmia Database(CUDB) using the neural network with weighted fuzzy membership functions(NEWFM) and wavelet transforms. In the first step, wavelet transforms are used to obtain the detail coefficients at levels 3 and 4. In the second step, all of detail coefficients d3 and d4 are classified into four intervals, respectively, and then the standard deviations of the specific intervals are used as eight numbers of input features of NEWFM. NEWFM classifies normal and VT/VF beats using eight numbers of input features, and then the accuracy rate is 90.1%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.17-22
• /
• 2014

Watermarking is one of the methods that insist on a copyright as it append digital signals in digital informations like still mobile image, video, other informations. This paper proposed an improved DCT-based watermarking scheme using quantized coefficients of image. This process makes quantized coefficients through a Discrete Cosine Transform and Quantization. The watermark is embedded into the quantization coefficients in accordance with location(key). The quantized watermarked coefficients are converted to watermarked image through the inverse quantization and inverse DCT. Watermark extract process only use watermarked image and location(key). In watermark extract process, quantized coefficients is obtained from watermarked image through a DCT and quantization process. The quantized coefficients select coefficients using location(key). We perform it using inverse DCT and get the watermark'. Simulation results are satisfied with high quality of image (PSNR) and Normalized Correlation(NC) from the watermarked image and the extracted watermark.