• 음성과학
• /
• 제9권2호
• /
• pp.135-146
• /
• 2002

Generally a speaker verification system improves its system recognition ratio by regularizing log likelihood ratio, using a speaker model and its background speaker model that are required to be verified. The speaker-based cohort method is one of the methods that are widely used for selecting background speaker model. Recently, Gaussian-based cohort model has been suggested as a virtually synthesized cohort model, and unlike a speaker-based model, this is the method that chooses only the probability distributions close to basic speaker's probability distribution among the several neighboring speakers' probability distributions and thereby synthesizes a new virtual speaker model. It shows more excellent results than the existing speaker-based method. This study compared the existing speaker-based background speaker models and virtual speaker models and then constructed new virtual background speaker model groups which combined them in a certain ratio. For this, this study constructed a speaker verification system that uses GMM (Gaussin Mixture Model), and found that the suggested method of selecting virtual background speaker model shows more improved performance.

• 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.

• 한국멀티미디어학회논문지
• /
• 제9권12호
• /
• pp.1607-1616
• /
• 2006

The growing market of multimedia and digital signal processing requires significant data-path portions of SoCs. However, the common models for verification are not suitable for SoCs. A novel model--WGL (Weighted Generalized List) is proposed, which is based on the general-list decomposition of polynomials, with three different weights and manipulation rules introduced to effect node sharing and the canonicity. Timing parameters and operations on them are also considered. Examples show the word-level WGL is the only model to linearly represent the common word-level functions and the bit-level WGL is especially suitable for arithmetic intensive circuits. The model is proved to be a uniform and efficient model for both bit-level and word-level functions. Then Based on the WGL model, a backward-construction logic-verification approach is presented, which reduces time and space complexity for multipliers to polynomial complexity(time complexity is less than $O(n^{3.6})$ and space complexity is less than $O(n^{1.5})$) without hierarchical partitioning. Finally, a construction methodology of word-level polynomials is also presented in order to implement complex high-level verification, which combines order computation and coefficient solving, and adopts an efficient backward approach. The construction complexity is much less than the existing ones, e.g. the construction time for multipliers grows at the power of less than 1.6 in the size of the input word without increasing the maximal space required. The WGL model and the verification methods based on WGL show their theoretical and applicable significance in SoC design.

• KEPCO Journal on Electric Power and Energy
• /
• 제7권1호
• /
• pp.115-123
• /
• 2021

Through machine learning-based load prediction, it is possible to prevent excessive power generation or unnecessary economic investment by estimating the appropriate amount of facility investment in consideration of the load that will increase in the future or providing basic data for policy establishment to distribute the maximum load. However, in order to secure the reliability of the developed load prediction model in the field, the performance comparison verification between the distribution line load prediction models must be preceded, but a comparative performance verification system between the distribution line load prediction models has not yet been established. As a result, it is not possible to accurately determine the performance excellence of the load prediction model because it is not possible to easily determine the likelihood between the load prediction models. In this paper, we developed a reliability verification system for load prediction models including a method of comparing and verifying the performance reliability between machine learning-based load prediction models that were not previously considered, verification process, and verification result visualization methods. Through the developed load prediction model reliability verification system, the objectivity of the load prediction model performance verification can be improved, and the field application utilization of an excellent load prediction model can be increased.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.285-288
• /
• 2004

In this paper, we present a design and experiment of PCI Express core verification model. The model targeting Endpoint core based on Verilog HDL is designed by newly-emerging SystemC, which is a new C++ class library based system design approach. In the verification model, we designed and implemented a SystemC host system model which acted as Root Complex and device driver dedicated to the PCI Express Endpoint RTL core. The verification process is scheduled by scenarios which are implemented in host model. We show that the model is useful especially for verifying the RTL model which has dependencies on system software.

• 대한음성학회지:말소리
• /
• 제63호
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• 디지털산업정보학회논문지
• /
• 제10권4호
• /
• pp.127-132
• /
• 2014

Some laws and regulations may require internet service providers to provide services based on the age of users. Age verification in the online environment should be used as a tool to provide service that is appropriate to child based on age. Using the minimum attribute information, processes on age verification provides the proper guidance to the internet services. However, there is a lack of a globally accepted trust framework for age verification process including evaluation factors for age verification information. In this paper the federation model of user attributes were described and evaluation factors for the age verification information were suggested. Also using the suggested evaluation factors, performance evaluation of federation model of user evaluation was performed. To meet the requirements of evaluation factors, framework of federation model should consider the unlinkability pseudonym support, eavesdropping protection and cloning protection.

• 한국음향학회지
• /
• 제29권3호
• /
• pp.216-221
• /
• 2010

본 논문에서는 Gaussian Mixture Model (GMM)-supervector의 Mahalanobis 거리측정 방법 기반의 Support Vector Machine (SVM) 커널을 이용한 새로운 화자인증 방법을 제안한다. 제안된 GMM-supervector SVM 커널방식은 GMM 방식과 SVM 방식을 결합한 방식으로서, GMM 파라미터에 의해 형성된 화자 및 비 화자 GMM-supervectors의 화자인증 임계값을 Mahalanobis 거리측정 방법기반의 SVM 커널에 적용함으로써 화자인증 정확도를 높인다. 제안한 방식의 성능 측정을 위해 20명의 화자를 대상으로 문장독립형 화자인증 실험을 수행하여 기존에 사용되고 있는 GMM, SVM, Kullback-Leibler (KL) divergence 거리측정 방법 기반의 GMM-supervector SVM 커널, Bhattacharyya 거리측정 방법기반의 GMM-supervector SVM 커널 방식을 통한 화자인증 결과들과 비교하였다.

• 대한음성학회지:말소리
• /
• 제49호
• /
• pp.145-158
• /
• 2004

This paper is aiming at implementation of real-time speaker verification system using DSP board. Dialog/4, which is based on microprocessor and DSP processor, is selected to easily control telephone signals and to process audio/voice signals. Speaker verification system performs signal processing and feature extraction after receiving voice and its ID. Then through computing the likelihood ratio of claimed speaker model to the background model, it makes real-time decision on acceptance or rejection. For the verification experiments, total 15 speaker models and 6 background models are adopted. The experimental results show that verification accuracy rates are 99.5% for using telephone speech-based speaker models.

• 음성과학
• /
• 제10권2호
• /
• pp.35-43
• /
• 2003

General speaker verification systems improve their recognition performances by normalizing log likelihood ratio, using a speaker model and its background speaker model that are required to be verified. So these systems rely heavily on the availability of much speaker independent databases for background speaker model design. This constraint, however, may be a burden in practical and portable devices such as palm-top computers or wireless handsets which place a premium on computations and memory. In this paper, new approach for the GMM-based background model design used in portable speaker verification system is presented when the enrollment data is available. This approach is to modify three parameters of GMM speaker model such as mixture weights, means and covariances along with reduced mixture order. According to the experiment on a 20 speaker population from YOHO database, we found that this method had a promise of effective use in a portable speaker verification system.