• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.451-454
• /
• 2005

Recently, many methods to analyze signal have been proposed and representative methods are the Fourier transform and wavelet transform. In these methods, the Fourier transform represents signal with combination cosine and sine at all locations in the frequency domain. However, it doesn't provide time information that particular frequency occurs in signal and depends on only the global feature of the signal. So, to improve these points the wavelet transform which is capable of multiresolution analysis has been applied to many fields such as speech processing, image processing and computer vision. And the wavelet transform, which uses changing window according to scale parameter, presents time-frequency localization. In this paper, we proposed a new approach using a wavelet of cosine and sine type and analyzed features of signal in a limited point of frequency-time plane.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1759-1769
• /
• 1997

The Error BackPropagation (EBP) algorithm for multi-layered neural networks is widely used in various areas such as associative memory, speech recognition, pattern recognition and robotics, etc. Nevertheless, many researchers have continuously published papers about improvements over the original EBP algorithm. The main reason for this research activity is that EBP is exceeding slow when the number of neurons and the size of training set is large. In this study, we developed new learning speed acceleration methods using variable learning rate, variable momentum rate and variable slope for the sigmoid function. During the learning process, these parameters should be adjusted continuously according to the total error of network, and it has been shown that these methods significantly reduced learning time over the original EBP. In order to show the efficiency of the proposed methods, first we have used binary data which are made by random number generator and showed the vast improvements in terms of epoch. Also, we have applied our methods to the binary-valued Monk's data, 4, 5, 6, 7-bit parity checker and real-valued Iris data which are famous benchmark training sets for machine learning.

• Journal of KIISE:Software and Applications
• /
• v.27 no.1
• /
• pp.84-95
• /
• 2000

In this paper, we propose an integrated indexing method with compound noun segmentation and noun phrase synthesis. Statistical information is used in the compound noun segmentation and natural language processing techniques are carefully utilized in the noun phrase synthesis. Firstly, we choose index terms from simple words through morphological analysis and part-of-speech tagging results. Secondly, noun phrases are automatically synthesized from the syntactic analysis results. If syntactic analysis fails, only morphological analysis and tagging results are applied. Thirdly, we select compound nouns from the tagging results and then segment and re-synthesize them using statistical information. In this way, segmented and synthesized terms are used together as index terms to supplement the single terms. We demonstrate the effectiveness of the proposed integrated indexing method for Korean compound noun processing using KTSET2.0 and KRIST SET which are a standard test collection for Korean information retrieval.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1111-1120
• /
• 2022

Image Capturing is a matter of viewing images and describing images in language. The problem is an important problem that can be solved by keeping, understanding, and bringing together two areas of image processing and natural language processing. In addition, by automatically recognizing and describing images in text, images can be converted into text and then into speech for visually impaired people to help them understand their surroundings, and important issues such as image search, art therapy, sports commentary, and real-time traffic information commentary. So far, the image captioning research approach focuses solely on recognizing and texturing images. However, various environments in reality must be considered for practical use, as well as being able to provide image descriptions for the intended purpose. In this work, we limit the universally available Korean and English image captioning models and text generation techniques for the purpose of image captioning.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.2
• /
• pp.192-198
• /
• 2022

As an effective weapon system for anti-submarine warfare, DIrectional Frequency Analysis and Recording (DIFAR) sonobuoy detects underwater targets via beamforming with three channels composed of an omni-direcitonal and two directional channels. However, ambient noise degrades the detection performance of DIFAR sonobouy in specific direction (0°, 90°, 180°, 270°). Thus, an ambient noise redcution technique is proposed for performance improvement of acoustic target detection of DIFAR sonobuoy. The proposed method is based on OTA (Order Truncate Average), which is widely used in sonar signal processing area, for ambient noise estimation and Wiener filtering, which is widely used in speech signal processing area, for noise reduction. For evaluation, we compare mean square errors of target bearing estmation results of conventional and proposed methods and we confirmed that the proposed method is effective under 0 dB signal-to-noise ratio.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.10
• /
• pp.935-943
• /
• 2017

CNN (Convolution neural network), which is used for image classification and speech recognition among neural networks learning based on positive data, has been continuously developed to have a high performance structure to date. There are many difficulties to utilize in an embedded system with limited resources. Therefore, we use GPU (General-Purpose Computing on Graphics Processing Units), which is used for general-purpose operation of GPU to solve the problem because we use pre-learned weights but there are still limitations. Since CNN performs simple and iterative operations, the computation speed varies greatly depending on the thread allocation and utilization method in the Single Instruction Multiple Thread (SIMT) based GPGPU. To solve this problem, there is a thread that needs to be relaxed when performing Convolution and Pooling operations with threads. The remaining threads have increased the operation speed by using the method used in the following feature maps and kernel calculations.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.161-170
• /
• 2024

With the technological advances, the humans have made so much progress in the ease of living and now incorporating the use of sight, motion, sound, speech etc. for various application and software controls. In this paper, we have explored the project in which gestures plays a very significant role in the project. The topic of gesture control which has been researched a lot and is just getting evolved every day. We see the usage of computer vision in this project. The main objective that we achieved in this project is controlling the computer settings with hand gestures using computer vision. In this project we are creating a module which acts a volume controlling program in which we use hand gestures to control the computer system volume. We have included the use of OpenCV. This module is used in the implementation of hand gestures in computer controls. The module in execution uses the web camera of the computer to record the images or videos and then processes them to find the needed information and then based on the input, performs the action on the volume settings if that computer. The program has the functionality of increasing and decreasing the volume of the computer. The setup needed for the program execution is a web camera to record the input images and videos which will be given by the user. The program will perform gesture recognition with the help of OpenCV and python and its libraries and them it will recognize or identify the specified human gestures and use them to perform or carry out the changes in the device setting. The objective is to adjust the volume of a computer device without the need for physical interaction using a mouse or keyboard. OpenCV, a widely utilized tool for image processing and computer vision applications in this domain, enjoys extensive popularity. The OpenCV community consists of over 47,000 individuals, and as of a survey conducted in 2020, the estimated number of downloads exceeds 18 million.

• ETRI Journal
• /
• v.36 no.5
• /
• pp.704-713
• /
• 2014

Most natural language processing tasks depend on the outputs of some other tasks. Thus, they involve other tasks as subtasks. The main problem of this type of pipelined model is that the optimality of the subtasks that are trained with their own data is not guaranteed in the final target task, since the subtasks are not optimized with respect to the target task. As a solution to this problem, this paper proposes a consolidation of subtasks for a target task ($CST^2$). In $CST^2$, all parameters of a target task and its subtasks are optimized to fulfill the objective of the target task. $CST^2$ finds such optimized parameters through a backpropagation algorithm. In experiments in which text chunking is a target task and part-of-speech tagging is its subtask, $CST^2$ outperforms a traditional pipelined text chunker. The experimental results prove the effectiveness of optimizing subtasks with respect to the target task.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.397-404
• /
• 2011

In this paper, we were carried out experiments to apply parameter of voice analysis to measure changing characteristic articulator according to inhale the helium gas. The helium gas was used to overcome air embolism nitrogen gas to deal a fatal blow in body nitrogen gas by diver. However, the helium gas has been much trouble interpretation about abnormal voice of diver to cause squeaky voice of low articulation. Therefor, we was carried out experiments about pitch and spectrogram measurement, analysis based on to influence in acoustic organs before and after of inhaled helium gas.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.5
• /
• pp.277-281
• /
• 2013

Modern speaker verification systems based on support vector machines (SVMs) use Gaussian mixture model (GMM) supervectors as their input feature vectors, and the maximum a posteriori (MAP) adaptation is a conventional method for generating speaker-dependent GMMs by adapting a universal background model (UBM). MAP adaptation requires the appropriate amount of input utterance due to the number of model parameters to be estimated. On the other hand, with limited utterances, unreliable MAP adaptation can be performed, which causes adaptation noise even though the Bayesian priors used in the MAP adaptation smooth the movements between the UBM and speaker dependent GMMs. This paper proposes a sparse MAP adaptation method, which is known to perform well in the automatic speech recognition area. By introducing sparse MAP adaptation to the GMM-SVM-based speaker verification system, the adaptation noise can be mitigated effectively. The proposed method utilizes the L0 norm as a regularizer to induce sparsity. The experimental results on the TIMIT database showed that the sparse MAP-based GMM-SVM speaker verification system yields a 42.6% relative reduction in the equal error rate with few additional computations.