• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.51-55
• /
• 2019

This paper proposes a speech enhancement method utilizing the feature compensation gain for robust speech recognition performances in noisy environments. In this paper we propose a speech enhancement method utilizing the feature compensation gain which is obtained from the PCGMM (Parallel Combined Gaussian Mixture Model)-based feature compensation method employing variational model composition. The experimental results show that the proposed method significantly outperforms the conventional front-end algorithms and our previous research over various background noise types and SNR (Signal to Noise Ratio) conditions in mismatched ASR (Automatic Speech Recognition) system condition. The computation complexity is significantly reduced by employing the noise model selection technique with maintaining the speech recognition performance at a similar level.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2367-2374
• /
• 2014

This paper proposes a speech enhancement method which can be independently applied to different types of speech recognition systems. Feature compensation methods are well known to be effective as a front-end algorithm for robust speech recognition in noisy environments. The feature types and speech model employed by the feature compensation methods should be matched with ones of the speech recognition system for their effectiveness. However, they cannot be successfully employed by the speech recognition with "unknown" specification, such as a commercialized speech recognition engine. In this paper, a speech enhancement method is proposed, which is based on the PCGMM-based feature compensation method. The experimental results show that the proposed method significantly outperforms the conventional front-end algorithms for unknown speech recognition over various background noise conditions.

• Proceedings of the KIPE Conference
• /
• 2016.07a
• /
• pp.28-29
• /
• 2016

본 논문에서는 자이레이터를 사용하여 자기유도 전력전달시스템의 보상 회로를 해석하는 방식을 제안한다. 보상회로를 주로 구성하는 갖가지 공진 회로와 유도 결합 코일이 자이레이터의 특성을 가지고 있음을 보인다. 그러므로, 자이레이터의 바람직한 특성들을 보상 회로의 전원-로드 이득, 전원의 역률 등을 해석하는데 사용할 수 있음을 보인다. 제안된 방식은 수식 기반이 아닌 회로 기반의 해석 방식이라 적용이 간편하고, 모든 주파수 영역에서도 해석이 가능하며, 코일의 직렬 기생 저항 또한 포함할 수 있다는 특징이 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.5
• /
• pp.34-45
• /
• 1997

In this paper, we present hardware implemcntation of self-organizing feature map (SOFM) neural networkwith constant adaptation gain and binary reinforcement function on FPGA. Whereas a tnme-varyingadaptation gain is used in the conventional SOFM, the proposed SOFM has a time-invariant adaptationgain and adds a binary reinforcement function in order to compensate for the lowered abilityof SOFM due to the constant adaptation gain. Since the proposed algorithm has no multiplication operation.it is much easier to implement than the original SOFM. Since a unit neuron is composed of 1adde $r_tracter and 2 adders, its structure is simple, and thus the number of neurons fabricated onFPGA is expected to he large. In addition, a few control signal: ;:rp sufficient for controlling !he neurons.Experimental results show that each componeni ot thi inipiemented neural network operates correctlyand the whole system also works well.stem also works well.

• Proceedings of the KIPE Conference
• /
• 2018.07a
• /
• pp.21-23
• /
• 2018

본 논문에서는 능동형 스너버를 사용한 비대칭 하프-브리지 컨버터를 제안한다. 비대칭 하프-브리지 컨버터는 홀드-업 시간을 고려하여 넓은 입력전압 범위에서 설계되면, 노미널 동작 시 작은 시비율로 동작하여 변압기에 큰 오프셋 전류가 발생한다. 또한 변압기가 작은 턴 비로 설계되어 1차측 전류 스트레스와 2차측 정류기의 전압 스트레스가 커지는 문제점이 있다. 이러한 문제점들을 해결하기 위해, 제안하는 컨버터에서는 추가 스위치를 사용해 추가적인 전압이득을 얻음으로써, 홀드-업동작 시 낮아지는 입력 전압을 보상한다. 때문에 제안하는 컨버터는 홀드-업 상태를 고려하지 않고 설계될 수 있어, 노미널 시에 큰 시비율로 동작한다. 게다가 추가 스위치는 능동형 스너버로 사용되어 2차측 정류기 다이오드의 전압 링잉을 제거하여 전압 스트레스를 저감시킨다. 이와 같은 특징으로 인하여 제안하는 컨버터는 전 부하 영역에서 높은 효율을 갖는다. 제안하는 컨버터의 효용성을 검증하기 위해 320-410V 입력전압과 19.5V/200W 출력에서 실험이 진행되었다.

• Journal of IKEEE
• /
• v.16 no.2
• /
• pp.69-75
• /
• 2012

In this paper, microstrip array antenna is proposed for the wireless communication of DSRC(dedicated short range communication) scheme at 5.8GHz, which works as a part of the Navigation terminal. The microstrip patches minimized from a rectangular microstrip antenna with a half wavelength are arrayed to be mounted on the narrow and long area in the top side of the navigation terminal. Besides, the array antenna can limit its own beamwidth to the driving lane and has better directivity. It is simulated to verify the validity of the proposed application. The prototype fabricated has a volume of $18{\times}40{\times}0.8mm^3$. From the measurement, it has circular polarization performance of 4dB axial ratio over 40MHz frequency band. In addition, antenna gain of 6.2dBi and 3dB beamwidth of $70^{\circ}$ at cross section of driving lane have been achieved.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.299-305
• /
• 2022

Analog-digital converter (ADC) should be one of the most important blocks that convert various physical signals to digital ones for signal processing in the digital signal domain. As most operations of the analog circuit for sensor signal processing have been replaced by digital circuits, high-resolution performance is required for ADC. In addition, low-power must be the critical issue in order to extend the battery time of mobile system. The existing integrating sigma-delta ADCs has a characteristic of high resolution, but due to its low supply voltage condition and advanced technology, circuit error and corresponding resolution degradation of ADC result from the finite gain of the operational amplifier in the integrator. Buffer compensation technique can be applied to minimize gain errors, but there is a disadvantage of additional power dissipation due to the added buffer. In this paper, incremental signal-delta ADC is proposed with buffer switching scheme to minimize current and igh-pass bias circuit to improve the settling time.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.2
• /
• pp.49-57
• /
• 2003

In this paper, is proposed an anti-swing control algorithm for the automation of overhead crane. The algorithm consists of three parts, the FCL with compensatory FLC which generates acceleration, velocity and position reference to reduce swing angle and acceleration feedback controller which feedback control errors. Especially the algorithm dose not need angular sensor which detect swing angle of payload and requires high cost. By the simulation study and experiment with prototype crane, we showed the usefulness of the proposed algorithm.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.73-81
• /
• 2018

The quality of side scan sonar images is determined by the frequency of a sonar. A side scan sonar with a low frequency creates low-quality images. One of the factors that lead to low quality is a high-level noise. The noise is occurred by the underwater environment such as equipment noise, signal interference and so on. In addition, in order to compensate for the transmission loss of sonar signals, the received signal is recovered by TVG (Time-Varied Gain), and consequently the side scan sonar images contain non-homogeneous noise which is opposite to optic images whose noise is assumed as homogeneous noise. In this paper, the SSCS (Structural Sparsity based Compressive Sensing) is proposed for removing non-homogeneous noise. The algorithm incorporates both local and non-local models in a structural feature domain so that it guarantees the sparsity and enhances the property of non-local self-similarity. Moreover, the non-local model is corrected in consideration of non-homogeneity of noises. Various experimental results show that the proposed algorithm is superior to existing method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.4
• /
• pp.1087-1099
• /
• 1998

In the content-based image coding, where each object in the scene is encoded independently, the shape, texture and motion information are very important factors. Though the contours representing the shape of an object occupy a great amount of data in proportion to the whole information, they strongly affect the subjective image quaility. Therefore, the distortion of contour coding has to be minimized as much as possible. In this paper, we propose a new method for the contour coding in which the contours are approximated to polygon and the eorror signal occurring from polygonal approximation are transformed with new basis functions. Considering the facts that confour segments occurring from polygonal approximation are smooth curves and error signals have two zero-ending points, we design new basis functions based on the Legendre polynomial and then transform the error signals with them. When applied to synthetic images such as circles, ellipses and etc., the proposed method provides, in overall, outstanding results in respect to the transform coding gain compared with DCT and DST. And in the case when applied to natural images, the proposed method gives better image quality over DCT and comparable results with DST.