• 음성과학
• /
• 제9권1호
• /
• pp.49-59
• /
• 2002

This paper concerns an effective text-dependent speaker verification method to increase the performance of speaker verification. While various speaker verification methods have already been developed, their effectiveness has not yet been formally proven in terms of achieving acceptable performance levels. This paper proposes a weighted likelihood procedure along with a confidence measure based on subword-based text-dependent speaker verification. Our aim is to remedy the low performance problem in speaker verification by exploring a means to strengthen the verification likelihood via subword-based hypothesis criteria and weighted likelihood method. Experimental results show that the proposed speaker verification method outperforms that of the speaker verification scheme without using the proposed decision by a factor of up to 1.6 times. From these results, the proposed speaker verification method is shown to be very effective and to achieve a reliable performance.

• 음성과학
• /
• 제7권4호
• /
• pp.41-47
• /
• 2000

This paper concerns an effective text-prompted speaker verification method to increase the performance of speaker verification. While various speaker verification methods have already been developed, their effectiveness has not yet been formally proven in terms of achieving an acceptable performance level. It is also noted that the traditional methods were focused primarily on single, prompted utterance for verification. This paper, instead, proposes sequential decision method using variable threshold focused at handling two utterances for text-prompted speaker verification. Experimental results show that the proposed speaker verification method outperforms that of the speaker verification scheme without using the sequential decision by a factor of up to 3 times. From these results, we show that the proposed method is highly effective and achieves a reliable performance suitable for practical applications.

• 대한전자공학회논문지SD
• /
• 제44권6호
• /
• pp.83-88
• /
• 2007

본 논문에서는 유기발광다이오드 구동 IC의 기능을 검증하기 위하여 PLI(Programing Language Interface)를 이용한 검증방법을 제안한다. 기능 검증을 하기 위하여 HDL(Hardware Description Language) 시뮬레이터와 PLI, GUI(Graphic User Interface) 환경의 이미지 뷰어를 이용한다. 본 논문에서 제안하는 유기발광다이오드 구동 IC의 기능 검증 방법을 이용 할 경우 종래의 기능 검증 방법을 이용 할 때 보다 40배의 실행 시간 이득을 얻을 수 있다. 제안한 방법을 이용할 경우 디스플레이 구동 IC의 설계 단계에서 기능 검증을 효율적으로 할 수 있을 것이다.

• 한국철도학회논문집
• /
• 제7권2호
• /
• pp.114-119
• /
• 2004

According to the computerization of railway signalling systems. the communication protocol for interface between these systems are required. Therefore the new communication protocol for railway signaling system is required. Generally, there are two verification method for new designed protocol in the industrial and academic fields. One is the laboratory testing method which is very popular and general technique. In our research the comparison between existing and new designed protocol for signaling is described and the verification test results are also represented. From these laboratory test, we are verified the conformance of new designed protocol. Another method is verified by formal method. The format verification method is widely used at safety-critical system design but this approach is nor popular at verification communication protocol. However it is very important to verify the safety of new designed protocol for railway signaling system because signaling systems are very safety-critical systems. So, the methodology for formal verification of designed protocol is also reviews in this paper.

• Journal of Information Processing Systems
• /
• 제12권3호
• /
• pp.381-391
• /
• 2016

The Joint Bayesian (JB) method has been used in most state-of-the-art methods for face verification. However, since the publication of the original JB method in 2012, no improved verification method has been proposed. A lot of studies on face verification have been focused on extracting good features to improve the performance in the challenging Labeled Faces in the Wild (LFW) database. In this paper, we propose an improved version of the JB method, called the two-dimensional Joint Bayesian (2D-JB) method. It is very simple but effective in both the training and test phases. We separated two symmetric terms from the three terms of the JB log likelihood ratio function. Using the two terms as a two-dimensional vector, we learned a decision line to classify same and not-same cases. Our experimental results show that the proposed 2D-JB method significantly outperforms the original JB method by more than 1% in the LFW database.

• 제어로봇시스템학회논문지
• /
• 제2권1호
• /
• pp.53-59
• /
• 1996

An automatic verification method has been studied to determine the safety and operability of programmable logic controller (PLC) based systems. For the systematic and efficient verification, we have developed a conversion method from relay ladder logic (RLL) to the verification system description. RLL is a common representation used to document PLC programs for the sequential logic of the system such as the safety interlocks and the startup/shutdown procedures. Once the modules are developed, complex RLLs can be represented by the combination of modules. As a result we can verify complex PLC systems using the verification method including RLL modules. The developed modules are used to verify alarm systems and show that the method is valid.

• 대한음성학회지:말소리
• /
• 제51호
• /
• pp.71-84
• /
• 2004

In this paper, we propose the automatic speech database verification method(or called automatic verification) based on confidence measure for a large speech database. This method verifies the consistency between given transcription and speech using the confidence measure. The automatic verification process consists of two stages : the word-level likelihood computation stage and multi-level likelihood ratio computation stage. In the word-level likelihood computation stage, we calculate the word-level likelihood using the viterbi decoding algorithm and make the segment information. In the multi-level likelihood ratio computation stage, we calculate the word-level and the phone-level likelihood ratio based on confidence measure with anti-phone model. By automatic verification, we have achieved about 61% error reduction. And also we can reduce the verification time from 1 month in manual to 1-2 days in automatic.

• 한국통신학회논문지
• /
• 제34권3C호
• /
• pp.257-267
• /
• 2009

This paper presents a training method for neural networks and the employment of MSE (mean scare error) values as the basis of a decision regarding the identity claim of a speaker in a recurrent neural networks based speaker verification system. Recurrent neural networks (RNNs) are employed to capture temporally dynamic characteristics of speech signal. In the process of supervised learning for RNNs, target outputs are automatically generated and the generated target outputs are made to represent the temporal variation of input speech sounds. To increase the capability of discriminating between the true speaker and an impostor, a discriminative training method for RNNs is presented. This paper shows the use and the effectiveness of the MSE value, which is obtained from the Euclidean distance between the target outputs and the outputs of networks for test speech sounds of a speaker, as the basis of speaker verification. In terms of equal error rates, results of experiments, which have been performed using the Korean speech database, show that the proposed speaker verification system exhibits better performance than a conventional hidden Markov model based speaker verification system.

• Structural Engineering and Mechanics
• /
• 제65권2호
• /
• pp.203-211
• /
• 2018

This paper introduces the development process of NCC(New Concrete Cutting) system and analyzes first verification test. Based on the first verification test results, some problems of NCC system have been newly modified. We carry out the second verification test. We tried to verify cutting performance and dust control efficiency of NCC system through the cutting test of concrete bridge piers. In particular, this verification test strives to solve the problem of concrete dust, which is the biggest problem of dry cutting method. The remaining dust problems in cutting section tried to solve through this verification test. This verification test of the NCC system shows that the dust problem of dry cutting method is closely controlled and solved. In conclusion, the proposed NCC method is superior to the dry cutting method in all aspects, including cutting performance, dust vacuum efficiency and cooling effect. The proposed NCC system is believed to be able to provide eco-friendly cutting technology to various industries, such as the removal of the SOC structures and the dismantling of nuclear plants, which have recently become a hot issue in the field of concrete cutting.

• 전자공학회논문지CI
• /
• 제45권5호
• /
• pp.162-172
• /
• 2008

본 논문에서는 이동환경에서 개인의 신원을 인증하는 수단으로 치열영상과 음성을 생체정보로 이용한 멀티모달 화자인증 방법에 대하여 제안한다. 제안한 방법은 이동환경의 단말장치중의 하나인 스마트폰의 영상 및 음성 입력장치를 이용하여 생체 정보를 획득하고, 이를 이용하여 사용자 인증을 수행한다. 더불어, 제안한 방법은 전체적인 사용자 인증 성능의 향상을 위하여 두 개의 단일 생체인식 결과를 결합하는 멀티모달 방식으로 구성하였고, 결합 방법으로는 시스템의 제한된 리소스를 고려하여 비교적 간단하면서도 우수한 성능을 보이는 가중치 합의 방법을 사용하였다. 제안한 멀티모달 화자인증 시스템의 성능평가는 스마트폰에서 획득한 40명의 사용자에 대한 데이터베이스를 이용하였고, 실험 결과, 치열영상과 음성을 이용한 단일 생체인증 결과는 각각 8.59%와 11.73%의 EER를 보였으며, 멀티모달 화자인증 결과는 4.05%의 EER를 나타냈다. 이로부터 본 논문에서는 인증 성능을 향상하기 위하여 두 개의 단일 생체인증 결과를 간단한 가중치 합으로 결합한 결과, 높은 인증 성능의 향상을 도모할 수 있었다.