• Journal of Digital Convergence
• /
• v.11 no.6
• /
• pp.169-174
• /
• 2013

Speech recognition, the problem of performance degradation is the difference between the model training and recognition environments. Silence features normalized using the method as a way to reduce the inconsistency of such an environment. Silence features normalized way of existing in the low signal-to-noise ratio. Increase the energy level of the silence interval for voice and non-voice classification accuracy due to the falling. There is a problem in the recognition performance is degraded. This paper proposed a robust speech detection method in noisy environments using a silence feature normalization and voice energy maximize. In the high signal-to-noise ratio for the proposed method was used to maximize the characteristics receive less characterized the effects of noise by the voice energy. Cepstral feature distribution of voice / non-voice characteristics in the low signal-to-noise ratio and improves the recognition performance. Result of the recognition experiment, recognition performance improved compared to the conventional method.

• Journal of Korea Multimedia Society
• /
• v.13 no.8
• /
• pp.1128-1141
• /
• 2010

This paper proposes a method of moving object detection in crowded scene using clustered trajectory. Unlike previous appearance based approaches, the proposed method employes motion information only to isolate moving objects. In the proposed method, feature points are extracted from input frames first and then feature tracking is followed to create feature trajectories. Based on an assumption that feature points originated from the same objects shows similar motion as the object moves, the proposed method detects moving objects by clustering trajectories of similar motions. For this purpose an energy function based on spatial proximity, motion coherence, and temporal continuity is defined to measure the similarity between two trajectories and the clustering is achieved by minimizing the energy function in CRFs (conditional random fields). Compared to previous methods, which are unable to separate falsely merged trajectories during the clustering process, the proposed method is able to rearrange the falsely merged trajectories during iteration because the clustering is solved my energy minimization in CRFs. Experiment results with three different crowded scenes show about 94% detection rate with 7% false alarm rate.

• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.344-348
• /
• 2009

Cognitive Radio(CR)는 특정 주파수 대역을 사용하도록 할당된 유저가 사용하지 않을 때, 이를 탐지하여 해당 주파수 대역을 이용함으로써 주파수 스펙트럼 효율을 향상시킬 수 있는 기술이다. 특히, CR에서 스펙트럼 센싱(Spectrum Sensing)은 중요한 기술의 하나라고 말할 수 있다. 기존의 스펙트럼 센싱 성능을 향상시키기 위한 방법으로, 다수의 노드가 각각 판정한 결과를 이용하는 OR-Rule, AND-Rule 등의 기법이 제안된 바 있다. 본 논문에서는 수신 다이버시티 기법 중의 하나인 Equal Gain Combiner(EGC) 알고리듬 이용하여 스펙트럼 센싱 성능을 알아보고 특히, 기존의 방법은 각 노드에서 판정 후 판정부에서 그 결과를 결합하여 최종 판정하는 방법이나, 본 논문에서 적용한 EGC 기법은 각 노드에서 수신된 신호에 대한 검출된 에너지 값을 융합센터(Fusion Center)로 보내어 최종 판정하는 방법이다. 각 노드에서 검출된 에너지 값을 융합센터가 수신한 신호에는 실질적으로 잡음이 섞이게 되므로 이로 인하여 발생할 수 있는 전송 오류를 추가적으로 고려하였다. 또한, 각 노드에서 검출한 에너지 값이 융합센터로 전송될 때에는 양자화 되어서 전송된다. 이에 따라서 양자화 bit수와 관련된 센싱 성능과 데이터의 반복 전송의 필요성, 그리고 그 횟수에 대해 제시하고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.150-151
• /
• 2010

본 논문에서는 잡음환경에서의 이중채널 음성인식을 위한 통계모델 기반 음성구간 검출 방법을 제안한다. 제안된 방법에서는 다채널 입력 신호로부터 얻어진 공간정보를 이용하여 음성 존재 및 부재 확률모델을 구하고 이를 통해 음성구간 검출을 행한다. 이때, 공간정보는 두 채널간의 상호 시간 차이와 상호 크기 차이로, 음성 존재 및 부재 확률은 가우시안 커널 밀도 기반의 확률모델로 표현된다. 그리고 음성구간은 각 시간 프레임 별 음성 존재 확률 대비 음성 부재 확률의 비를 추정하여 검출된다. 제안된 음성구간 검출 방법의 평가를 위해 검출된 구간만을 입력으로 하는 음성인식 성능을 측정한다. 실험결과, 제안된 공간정보를 이용하는 통계모델 기반의 음성구간 검출 방법이 주파수 에너지를 이용하는 통계모델 기반의 음성구간 검출 방법과 주파수 스펙트럼 밀도 기반 음성구간 검출 방법에 비해 각각 15.6%, 15.4%의 상대적 오인식률 개선을 보였다.

• Journal of Radiation Protection and Research
• /
• v.26 no.2
• /
• pp.73-78
• /
• 2001

In order to find the exposure conversion coefficients for 3"X3" NaI spectrum, we measured the exposure rates with the pressurized ion chamber at 29 different areas in the range of $4{\sim}23{\mu}R\;h^{-1}$, and also measured the gamma spectra with 3"X3" and 4"X4" NaI detectors, simultaneously. The exposure conversion coefficient of the total energy method was determined using the linear relation between the measured exposure rate and the gamma spectrum energy. In order to find the exposure conversion coefficients of the energy band method, we applied the exposure conversion coefficients recommended by NCRP to the 4"X4" NaI spectra, and calculated the exposure rates due to $^{40}K,\;^{238}U$, and $^{232}Th$ series respectively. Using the linearly proportional relation between the obtained $^{232}Th$ series exposure rate and peak area of 2614 keV that represents the $^{232}Th$ series, we obtained the exposure conversion coefficients for $^{232}Th$ series. We also determined the conversion coefficients for $^{238}U$ series and $^{40}K$ using a similar method.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.361-368
• /
• 2006

In this paper we present a snake-based scheme for efficiently detecting contours of objects with boundary concavities. The proposed method is composed of two steps. First, the object's boundary is detected using the proposed snake model. Second, snake points are optimized by inserting new points and deleting unnecessary points to better describe the object's boundary. The proposed algorithm can successfully extract objects with boundary concavities. Experimental results have shown that our algorithm produces more accurate segmentation results than the conventional algorithm.

• Journal of Radiation Protection and Research
• /
• v.26 no.2
• /
• pp.113-117
• /
• 2001

The energy band method for NaI spectrum calculates only the exposure rate due to natural radiation because it calculates exposure rate using energy spectrum of $1300{\sim}3000keV$. However, the total energy method includes in its calculation the exposure rate due to man-made radiation because it uses the energy spectrum of $150{\sim}3400keV$. Therefore, the resulting difference of extracting the exposure rate calculated by the energy band method from the exposure rate calculated by the total energy method is apparently the exposure rate due to man-made radiation. In this study, we measured the NaI spectrum during the period of significant changes of the exposure rate in the area without a man-made radiation. As the results, we found the exposure rates calculated by those two methods are equal within the statistical variation of ${\pm}0.3{\mu}R\;h^{-1}$. Consequently, if the difference between the exposure rates calculated by the two methods exists, it may be due to the man-made radiation exposure rate.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.11A
• /
• pp.1105-1116
• /
• 2008

Cognitive radio is one of the most effective techniques to improve the spectrum utilization efficiency. To implement the cognitive radio, spectrum sensing is considered as the key functionality because only counting on it, can the secondary users identify the spectrum holes and utilize them efficiently without causing interference to primary users. Generally, there are several spectrum sensing methods; the most common and simplest method is energy detection. However, the conventional energy detection has some disadvantages, which are caused by noise, especially, uncertain noise power leads to degradation of energy detector. In this paper, to solve this problem, we proposed sliding window-based energy detection method which can devide the frequency band of primary signal and noise using sliding window to estimate the power of primary user without the noise effect and achieve the better performance. It can calculate the energy of primary user only and can detect the primary signal. The simulation result shows that our proposed method outperforms conventional one.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.4
• /
• pp.343-350
• /
• 2016

In this paper, We proposed a realtime smoke detection using hidden markov model and DWT. The smoke type is not clear. The color of the smoke, form, spread direction, etc., are characterized by varying the environment. Therefore, smoke detection using specific information has a high error rate detection. Dynamic Object Detection was used a robust foreground extraction method to environmental changes. Smoke recognition is used to integrate the color, shape, DWT energy information of the detected object. The proposed method is a real-time processing by having the average processing speed of 30fps. The average detection time is about 7 seconds, it is possible to detect early rapid.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.447-453
• /
• 2009

This paper introduces the method for detect voices and exact end point at low SNR by maximizing voice energy. Conventional VAD (Voice Activity Detection) algorithm estimates noise level so it tends to detect the end point inaccurately. Moreover, because it uses relatively long analysis range for reflecting temporal change of noise, computing load too high for application. In this paper, the SEM-VAD (Speech Energy Maximization-Voice Activity Detection) method which uses psycho-acoustical bark scale filter banks to maximize voice energy within frames is introduced. Stable threshold values are obtained at various noise environments (SNR 15 dB, 10 dB, 5 dB, 0 dB). At the test for voice detection in car noisy environment, PHR (Pause Hit Rate) was 100%accurate at every noise environment, and FAR (False Alarm Rate) shows 0% at SNR15 dB and 10 dB, 5.6% at SNR5 dB and 9.5% at SNR0 dB.