• Speech Sciences
• /
• v.9 no.1
• /
• 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.

• Speech Sciences
• /
• v.7 no.4
• /
• 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.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.6 s.360
• /
• pp.83-88
• /
• 2007

In this paper, we propose the function verification method of the OLED(Organic Light Emitting Diode) drive IC using PLI verification method. This method uses the HDL(Hardware Description Language) simulator, PLI(Programing Language Interface), and GUI (Graphic User Interface) image viewer. This method improves the execute efficiency 40 times than conventional function verification methods. The proposed method can be used efficiently for function verification of DDI(display driver IC) design step.

• Journal of the Korean Society for Railway
• /
• v.7 no.2
• /
• 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
• /
• v.12 no.3
• /
• 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.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.1
• /
• 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.

• MALSORI
• /
• no.51
• /
• 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.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3C
• /
• 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
• /
• v.65 no.2
• /
• 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.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.162-172
• /
• 2008

In this paper, we propose a multimodal speaker verification method using teeth image and voice as biometric trait for personal verification in mobile terminal equipment. The proposed method obtains the biometric traits using image and sound input devices of smart-phone that is one of mobile terminal equipments, and performs verification with biometric traits. In addition, the proposed method consists the multimodal-fashion of combining two biometric authentication scores for totally performance enhancement, the fusion method is accompanied a weighted-summation method which has comparative simple structure and superior performance for considering limited resources of system. The performance evaluation of proposed multimodal speaker authentication system conducts using a database acquired in smart-phone for 40 subjects. The experimental result shows 8.59% of EER in case of teeth verification 11.73% in case of voice verification and the multimodal speaker authentication result presented the 4.05% of EER. In the experimental result, we obtain the enhanced performance more than each using teeth and voice by using the simple weight-summation method in the multimodal speaker verification system.