• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.807-823
• /
• 2018

Speaker verification system performance depends on the utterance of each speaker. To verify the speaker, important information has to be captured from the utterance. Nowadays under the constraints of limited data, speaker verification has become a challenging task. The testing and training data are in terms of few seconds in limited data. The feature vectors extracted from single frame size and rate (SFSR) analysis is not sufficient for training and testing speakers in speaker verification. This leads to poor speaker modeling during training and may not provide good decision during testing. The problem is to be resolved by increasing feature vectors of training and testing data to the same duration. For that we are using multiple frame size (MFS), multiple frame rate (MFR), and multiple frame size and rate (MFSR) analysis techniques for speaker verification under limited data condition. These analysis techniques relatively extract more feature vector during training and testing and develop improved modeling and testing for limited data. To demonstrate this we have used mel-frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) as feature. Gaussian mixture model (GMM) and GMM-universal background model (GMM-UBM) are used for modeling the speaker. The database used is NIST-2003. The experimental results indicate that, improved performance of MFS, MFR, and MFSR analysis radically better compared with SFSR analysis. The experimental results show that LPCC based MFSR analysis perform better compared to other analysis techniques and feature extraction techniques.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.1259-1262
• /
• 2004

Detecting environmental hazards and monitoring remote terrain are among many sensor network applications. In case of fire detection, it is significantly valuable to monitor fire-spot's shape and trend in time. Mobile ad hoc sensor nodes right round are responsible for sensoring, processing and networking packets, or even launching extinguisher. In this paper, we proposed a ring-oriented Multicast architecture based on "Fisheye State Routing" (MFSR) to organize a group of mobile ad hoc sensor nodes in a multicast way. It is familiar with traditional mesh-based multicast protocol [1] in mobile ad hoc network, trying to concentrates on efficiency and robustness simultaneously. Certain applications-based solution for hazards is proposed, quantitative results including architecture and recovery algorithms of MFSR are also investigated in this paper.

• The KIPS Transactions:PartC
• /
• v.8C no.4
• /
• pp.429-436
• /
• 2001

IMT-2000에서 RNC의 MCP는 호 처리를 담당하는 부분으로, 신뢰도와 실시간성이 요구된다. MCP는 높은 견고성을 갖도록 구현되지만 다소간의 오류 율(Fault late)은 존재할 수밖에 없으므로 프로세서를 이중화하여 활성화된 프로세서가 장애를 일으키더라도 대기중인 프로세서가 연속적인 서비스를 제공할 수 있어야한다. Warm standby sharing에 비하여 Hot standby sharing은 데이터 손실이 없고 오류 데이터가 확산되지 않는 등의 다수의 장점을 갖지만 동기화 문제로 인하여 이를 시스템에 실제로 구현하는 것은 어렵다. 따라서 본 연구에서는 Hot standby sharing에 비하여 기존의 Warm standby sharing이 갖는 동기화의 장점에 데이터 손실 및 거짓 데이터의 확산 문제를 개선함으로서, 실제 구현의 용이성 및 성능 향상이라는 결과를 얻으려 하였다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.14 no.2
• /
• pp.75-83
• /
• 2004

We present a realization of an LFSM that utilizes an LFSR. This is based on a well-known fact from linear algebra. This structure is used to show that a previous attempt at using a cellular automata in place of an LFSR in constructing a stream cipher did not necessarily increase its security. We also give a general method for checking whether or not a nonlinear filter generator based on an LFSM allows reduction to one that is based on an LFSR and which is vulnerable to Anderson information leakage.