• The Journal of the Acoustical Society of Korea
• /
• v.16 no.4
• /
• pp.57-63
• /
• 1997

In this paper, we study the efficient feature vector extraction method and front-end processing to improve the performance of the speech recognition system using KT(Korea Telecommunication) database collected through various telephone channels. First of all, we compare the recognition performances of the feature vectors known to be robust to noise and environmental variation and verify the performance enhancement of the recognition system using weighted cepstral distance measure methods. The experiment result shows that the recognition rate is increasedby using both PLP(Perceptual Linear Prediction) and MFCC(Mel Frequency Cepstral Coefficient) in comparison with LPC cepstrum used in KT recognition system. In cepstral distance measure, the weighted cepstral distance measure functions such as RPS(Root Power Sums) and BPL(Band-Pass Lifter) help the recognition enhancement. The application of the spectral subtraction method decrease the recognition rate because of the effect of distortion. However, RASTA(RelAtive SpecTrAl) processing, CMS(Cepstral Mean Subtraction) and SBR(Signal Bias Removal) enhance the recognition performance. Especially, the CMS method is simple but shows high recognition enhancement. Finally, the performances of the modified methods for the real-time implementation of CMS are compared and the improved method is suggested to prevent the performance degradation.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.173-176
• /
• 2001

In this thesis, a new measurement system is implemented for depth data extraction based on the camera calibration of the known pattern. The relation between 3D world coordinate and 2D image coordinate is analyzed. A new camera calibration algorithm is established from the analysis and then, the internal variables and external variables of the CCD camera are obtained. Suppose that the measurement plane is horizontal plane, from the 2D plane equation and coordinate transformation equation the approximation values corresponding minimum values using Newton-Rabbson method is obtained and they are stored into the look-up table for real time processing . A slit laser light is projected onto the object, and a 2D image obtained on the x-z plane in the measurement system. A 3D shape image can be obtained as the 2D (x-z)images are continuously acquired, during the object is moving to the y direction. The 3D shape images are displayed on computer monitor by use of OpenGL software. In a measuremental result, we found that the resolution of pixels have $\pm$ 1% of error in depth data. It seems that the error components are due to the vibration of mechanic and optical system. We expect that the measurement system need some of mechanic stability and precision optical system in order to improve the system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.11
• /
• pp.2715-2720
• /
• 2014

Median filtering is very effective to remove impulse type noises, so it has been widely used in many signal processing applications. However, due to the time complexity of its non-linearity, median filtering is often used using a small filter window size. A lot of work has been done on devising fast median filtering algorithms, but most of them can be efficiently applied to input data with finite integer values like images. Little work has been carried out on fast 2-d median filtering algorithms that can deal with real-valued 2-d data. In this paper, a fast and simple median 2-d filter is presented, and its performance is compared with the Matlab's 2-d median filter and a heap-based 2-d median filter. The proposed algorithm is shown to be much faster than the Matlab's 2-d median filter and consistently faster than the heap-based algorithm that is much more complicated than the proposed one. Also, a more efficient median filtering scheme for 2-d real valued data with a finite range of values is presented that uses higher-bit integer 2-d median filtering with negligible quantization errors.

• Journal of Broadcast Engineering
• /
• v.21 no.6
• /
• pp.977-985
• /
• 2016

In this paper, we propose a new method for on-line genre classification using spectrogram and deep neural network. For on-line processing, the proposed method inputs an audio signal for a time period of 1sec and classifies its genre among 3 genres of speech, music, and effect. In order to provide the generality of processing, it uses the spectrogram as a feature vector, instead of MFCC which has been widely used for audio analysis. We measure the performance of genre classification using real TV audio signals, and confirm that the proposed method has better performance than the conventional method for all genres. In particular, it decreases the rate of classification error between music and effect, which often occurs in the conventional method.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.1
• /
• pp.69-77
• /
• 1989

A hologram scanner for POS bar code symb9ol readers has been developed. This system is composed of scanning optics, optical detector, video signal circuitary and preprocessor. In contrast to conventional scanners using polygonal mirrors, which complicate the scanning optics, the hologram scanner developed in this research was made up with simple optics and higher reading performance was achieved. And in order to read abar code symbol omnidirectionally with highdensity scan patterns, the new real time decoding technique was proposed. The advantage of this technique is less hardware and lower clock rate. High speed processing and improved readability for tilted symbol was confirmed experimentally.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.9
• /
• pp.103-112
• /
• 1999

In this paper, a speaker-independent isolated world recognition system for a car navigation system is implemented using a general digital signal processor. This paper presents a method combining SNR normalization with RAS as a noise processing method. The semi-continuous hidden markov model is adopted and TMS320C31 is used in implementing the real-time system. Recognition word set is composed of 69 command words for a car navigation system. Experimental results showed that the recognition performance has a maximum of 93.62% in case of a combination of SNR normalization and spectral subtraction, and the performance improvement rate of the system is 3.69%, Presented noise processing method showed good speech recognition performance in 5dB SNR in car environment.

• The KIPS Transactions:PartB
• /
• v.10B no.5
• /
• pp.491-496
• /
• 2003

We present a new watermark design tool for digital images and digital videos that are based on human visual system (HVS) characteristics. In this tool, basic mechanisms (inhibitory and excitatory behaviour of cells) of HVS are used to determine image dependent upper bound values on watermark insertion. This allows us to insert maximai allowable transparent watermark, which in turn is extremely hard to attack with common image processing, Motion Picture Experts Group (MPEG) compression. As the number of details (e.g. edges) increases in an image, the HVS decrease its sensitivity to the details. In the same manner, as the number of motion increases in a video signal, the HVS decrease its sensitivity to the motions. We model this decreased sensitivity to the details and motions as an (motion) entropy masking. Entropy masking model can be efficiently used to increase the robustness of image and video watermarks. We have shown that our entropy-masking model provides watermark scheme with increased transparency and henceforth increased robustness.

• Annals of Clinical Neurophysiology
• /
• v.2 no.1
• /
• pp.8-12
• /
• 2000

Purpose : The rapid development and wide popularity of Digital EEG(DEEG) is due to its convenience, accuracy and applicability for quantitative analysis. These advantages of DEEG make one hesitate to use analog EEG(AEEG). To assess the advantage of DEEG system utilizing AEEG(DAEEG) over conventional AEEG and the clinical applicability, a DAEEG system was developed and applied to animal model Methods : Sprague-Dawley rat as status epilepticus model were used for collecting the EEG data. After four epidural electrodes were inserted and connected to 8-channel analog EEG(Nihon-Kohden, Japan), continous. EEG monitoring via computer screen was done from two rats simultaneously. EEG signals through analog amplifier and filters were digitized at digital signal processor and stored in Windows-based pentium personal computer. Digital data were sampled at a rate of 200 Hz and 12 bit of resolution. Acquisition software was able to carry out 'real-time view, sensitivity control and event marking' during continuous EEG monitoring. Digital data were stored on hard disk and hacked-up on CD-ROM for off-line review. Review system consisted of off-line review, saving and printing out interesting segment and annotation function. Results: This DAEEG system could utilize most major functions of DEEG sufficiently while making a use of an AEEG. It was easy to monitor continuously compared to Conventional AEEG and to control sensitivity during ictal period. Marking the event such as a clinical seizure or drug injection was less favorable than AEEG due to slowed processing speed of digital processor and central processing unit. Reviewing EEG data was convenient, but paging speed was slow. Storage and management of data was handy and economical. Conclusion : Relatively simple digital EEG system utilizing AEEG can be set-up at n laboratory level. It may be possible to make an application for clinical purposes.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.69-77
• /
• 2019

Today, most of elevators have an emergency call facility for emergency situations. However, if the network installed in the elevator is also out of power, it cannot be used for the elevator remote monitoring and management. So, we develop an integrated and unified emergency call system, which can transmit not only telephone call but also data signals using PSTN(Public Switched Telephone Network) in order to remote monitoring and management of elevators, even though a power outage occurs. The proposed integrated emergency call system to process multiple data such as voice and operational information is a multi-channel board system which is composed of an emergency phone signal processing module and an operational information processing module in the control box of elevator. In addition, the RMS(remote management server) systems based on the Web consist of a dial-up server and a remote monitoring server where manages the elevator's operating information, status records, and operational faults received via the proposed integrated and unified emergency call system in real time. So even if there's a catastrophic emergency, the proposed RMS systems shall ensure and maintain the safety of passengers inside the elevator. Also, remote control of the elevator by this system should be more efficient and secure. In near future, all elevator emergency call system need to support multifunctional capabilities to transmit operational data as well as phone calls for the safety of passengers. In addition, for safer elevators, it is necessary to improve them more efficiently by combining them with high-tech technologies such as the Internet of Things and artificial intelligence.

• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.127-132
• /
• 2020

The Smart Music Learning Device(SMLD) presented in this paper constructs the display part by attaching the touch panel to both sides of the transparent panel. The main processing unit uses raspberry pie, and the operating system uses Android. On the transparent panel, music education contents are displayed, and on the touch panels 1 and 2, the inputs of learners and instructors are accepted. The signal input from the touch panels 1 and 2 controls the progress of the music education contents through a process in the main processing unit. This control process design and implement a two - sided panel - based interactive training algorithm. This device aims at musical education based on mutual understanding. Therefore, it conducts face-to-face education using music education contents presented through transparent panel. This allows the instructor to know in real time the response to the learner, thus improving the understanding of the learning and the quality of the education. Also, the learner's concentration can be improved.