• The Journal of the Acoustical Society of Korea
• /
• 제17권2E호
• /
• pp.38-46
• /
• 1998

In this paper, we propose a remote speech input device, a new method of user-friendly speech input in spontaneous speech recognition system. We focus the user friendliness on hands-free and microphone independence in speech recognition applications. Our method adopts two algorithms, the automatic speech detection and the microphone array delay-and-sum beamforming (DSBF)-based speech enhancement. The automatic speech detection algorithm is composed of two stages; the detection of speech and nonspeech using the pitch information for the detected speech portion candidate. The DSBF algorithm adopts the time domain cross-correlation method as its time delay estimation. In the performance evaluation, the speech detection algorithm shows within-200 ms start point accuracy of 93%, 99% under 15dB, 20dB, and 25dB signal-to-noise ratio (SNR) environments, respectively and those for the end point are 72%, 89%, and 93% for the corresponding environments, respectively. The classification of speech and nonspeech for the start point detected region of input signal is performed by the pitch information-base method. The percentages of correct classification for speech and nonspeech input are 99% and 90%, respectively. The eight microphone array-based speech enhancement using the DSBF algorithm shows the maximum SNR gaing of 6dB over a single microphone and the error reductin of more than 15% in the spontaneous speech recognition domain.

• 음성과학
• /
• 제10권2호
• /
• pp.85-95
• /
• 2003

In speech signal processing, it is very important to detect the pitch exactly in speech recognition, synthesis and analysis. If we exactly pitch detect in speech signal, in the analysis, we can use the pitch to obtain properly the vocal tract parameter. It can be used to easily change or to maintain the naturalness and intelligibility of quality in speech synthesis and to eliminate the personality for speaker-independence in speech recognition. In this paper, we proposed a new pitch detection algorithm. First, positive center clipping is process by using the incline of speech in order to emphasize pitch period with a glottal component of removed vocal tract characteristic in time domain. And rough formant envelope is computed through peak-fitting spectrum of original speech signal infrequence domain. Using the roughed formant envelope, obtain the smoothed formant envelope through calculate the linear interpolation. As well get the flattened harmonics waveform with the algebra difference between spectrum of original speech signal and smoothed formant envelope. Inverse fast fourier transform (IFFT) compute this flattened harmonics. After all, we obtain Residual signal which is removed vocal tract element. The performance was compared with LPC and Cepstrum, ACF. Owing to this algorithm, we have obtained the pitch information improved the accuracy of pitch detection and gross error rate is reduced in voice speech region and in transition region of changing the phoneme.

• Advances in concrete construction
• /
• 제17권2호
• /
• pp.53-66
• /
• 2024

Domain Name Systems (DNS) provide critical performance in directing Internet traffic. It is a significant duty of DNS service providers to protect DNS servers from bandwidth attacks. Data mining techniques may identify different trends in detecting anomalies, but these approaches are insufficient to provide adequate methods for querying traffic data in significant network environments. The patterns can enable the providers of DNS services to find anomalies. Accordingly, this research has used a new approach to find the anomalies using the Neural Network (NN) because intrusion detection techniques or conventional rule-based anomaly are insufficient to detect general DNS anomalies using multi-enterprise network traffic data obtained from network traffic data (from different organizations). NN was developed, and its results were measured to determine the best performance in anomaly detection using DNS query data. Going through the R² results, it was found that NN could satisfactorily perform the DNS anomaly detection process. Based on the results, the security weaknesses and problems related to unpredictable matters could be practically distinguished, and many could be avoided in advance. Based on the R² results, the NN could perform remarkably well in general DNS anomaly detection processing in this study.

• 정보보호학회논문지
• /
• 제28권5호
• /
• pp.1141-1151
• /
• 2018

APT(Advanced Persistent Threat) 공격에서 감염 호스트와 C&C(Command and Control) 서버 간 통신은 공격 대상의 내부로 침입하기 위한 핵심단계이다. 공격자는 C&C 서버를 통해 다수의 감염 호스트를 제어하고, 침입 및 공격 행위를 지시하는데, 이 단계에서 C&C 서버가 노출되면 공격은 실패할 수 있다. 따라서 최근의 경우 DGA(Domain Generation Algorithm)를 통해 C&C 서버의 DNS를 짧은 시간 간격으로 교체하여 탐지를 어렵게 하고 있다. 특히 하루에도 500만개 이상 새로 등록되는 DNS 전부를 검증하고 탐지하는 것은 매우 어렵다. 이러한 문제점을 해결하기 위해 본 논문에서는 정상 DNS와 DGA를 통해 생성된 DNS(DGA-DNS)의 형태적 유사도(similarity) 분석을 이용한 DGA-DNS 탐지와 이를 통해 APT 공격 징후로 판단하는 모델을 제시하고 유효성을 검증한다.

• 대한의용생체공학회:의공학회지
• /
• 제29권6호
• /
• pp.466-476
• /
• 2008

The more people use ambulatory electrocardiogram(ECG) for arrhythmia detection, the more researchers report the automatic classification algorithms. Most of the previous studies don't consider the un-balanced data distribution. Even in patients, there are much more normal beats than abnormal beats among the data from 24 hours. To solve this problem, the hierarchical classification using 21 features was adopted for arrhythmia abnormal beat detection. The features include R-R intervals and data to describe the morphology of the wave. To validate the algorithm, 44 non-pacemaker recordings from physionet were used. The hierarchical classification model with 2 stages on domain knowledge was constructed. Using our suggested method, we could improve the performance in abnormal beat classification from the conventional multi-class classification method. In conclusion, the domain knowledge based hierarchical classification is useful to the ECG beat classification with unbalanced data distribution.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 추계종합학술대회
• /
• pp.1019-1022
• /
• 2005

최근 정보 통신 기술의 급속한 발전에 의해 음성 신호 처리에 관련된 많은 연구가 진행됨에 따라 피치 주기는 음성 인식, 화자 식별, 음성 분석 및 합성 등과 같은 많은 응용분야에서 중요한 요소로써 적용되고 있다. 이러한 피치 주기 검출에 관련된 시간 영역과 주파수 영역에서의 많은 알고리즘이 제안되었으며, 시간 영역의 피치 검출 알고리즘의 하나인 AMDF(average magnitude difference function)는 각 valley점의 거리를 피치 주기로 계산한다. 그러나 피치 주기 검출을 위한 valley점 선정에 있어서 알고리즘이 복잡해지는 문제점이 발생한다. 따라서 본 논문에서는 AMDF의 회전변환을 이용하여 전체 최소 valley점을 음성 신호의 피치 주기로 인식하는 간단한 알고리즘을 제안하였으며, 음성의 시작구간에 대해 경계값을 설정하여 피치 주기 선정에 대한 판단기준으로 사용하였다. 그리고 제안한 알고리즘을 시뮬레이션을 통해 기존의 방법들과 비교하였다.

• Smart Structures and Systems
• /
• 제18권3호
• /
• pp.501-523
• /
• 2016

Electromechanical impedance (EMI) based structural health monitoring is performed by measuring the variation in the impedance due to the structural local damage. The impedance signals are acquired from the piezoelectric patches that are bonded on the structural surface. The impedance variation, which is directly related to the mechanical properties of the structure, indicates the presence of local structural damage. Two traditional EMI-based damage detection methods are based on calculating the difference between the measured impedance signals in the frequency domain from the baseline and the current structures. In this paper, a new structural damage detection approach by analyzing the time domain impedance responses is proposed. The measured time domain responses from the piezoelectric transducers will be used for analysis. With the use of the Time Frequency Autoregressive Moving Average (TFARMA) model, a damage index based on Singular Value Decomposition (SVD) is defined to identify the existence of the structural local damage. Experimental studies on a space steel truss bridge model in the laboratory are conducted to verify the proposed approach. Four piezoelectric transducers are attached at different locations and excited by a sweep-frequency signal. The impedance responses at different locations are analyzed with TFARMA model to investigate the effectiveness and performance of the proposed approach. The results demonstrate that the proposed approach is very sensitive and robust in detecting the bolt damage in the gusset plates of steel truss bridges.

• 전기학회논문지
• /
• 제57권7호
• /
• pp.1295-1297
• /
• 2008

Large-sized flat-panel displays are widely used for PC monitors and TV displays. In this paper, frequency domain pre-filter algorithms are presented for detection of defects in large-sized Thin Film Transistor-Liquid Crystal Display(TFT-LCD) panel surfaces. Frequency analysis with 1-D, 2-D FFT methods for extract the periodic patterns of lattice structures in TFT-LCD is performed. To remove this patterns, frequency domain band-stop filters were used for eliminating specific frequency components. In order to acquire only defected images, 2-D inverse FFT methods to inverse transform of frequency domain images were used.

• 한국통신학회논문지
• /
• 제31권4C호
• /
• pp.458-471
• /
• 2006

Digital watermarking of multimedia data is a very active research area that has enjoyed a considerable amount of attention in recent years. In this paper, we propose an algorithm for embedding/detecting a fragile watermark in MPEG-4 compressed video domain (Simple and Advance Simple Profiles). The watermark bits are put directly into Huffman VLC-codespace of quantized DCT domain. The advantage of watermark embedding into the compressed domain is the significant savings for a real-time implementation as it does not require a full decoding operation. The watermark embedding does not change the video file size. The algorithm demonstrates high watermarking capacity, thereby providing reliable foolproof authentication. The results of experimental testing demonstrate that watermark embedding preserves the video quality. Watermark detection is performed without using the original video.

• 한국멀티미디어학회논문지
• /
• 제21권3호
• /
• pp.342-347
• /
• 2018

We proposed a fast detection of copy-move image forgery using four step search algorithm in the spatial domain. In the four-step search algorithm, the search area is 21 (-10 ~ +10), and the number of pixels to be scanned is 33. Our algorithm reduced computational complexity more than conventional copy move image forgery methods. The proposed method reduced 92.34 % of computational complexity compare to exhaustive search algorithm.