• The Journal of the Acoustical Society of Korea
• /
• v.23 no.6
• /
• pp.473-480
• /
• 2004

In this paper we propose an effective feature compensation scheme based on the speech model in order to achieve robust speech recognition. The proposed feature compensation method is based on parallel combined mixture model (PCMM). The previous PCMM works require a highly sophisticated procedure for estimation of the combined mixture model in order to reflect the time-varying noisy conditions at every utterance. The proposed schemes can cope with the time-varying background noise by employing the interpolation method of the multiple mixture models. We apply the‘data-driven’method to PCMM tot move reliable model combination and introduce a frame-synched version for estimation of environments posteriori. In order to reduce the computational complexity due to multiple models, we propose a technique for mixture sharing. The statistically similar Gaussian components are selected and the smoothed versions are generated for sharing. The performance is examined over Aurora 2.0 and speech corpus recorded while car-driving. The experimental results indicate that the proposed schemes are effective in realizing robust speech recognition and reducing the computational complexities under both simulated environments and real-life conditions.

• 한국정보통신설비학회:학술대회논문집
• /
• 2007.08a
• /
• pp.331-335
• /
• 2007

방송과 초고속인터넷 서비스를 동시에 제공할 수 있는 HFC(Hybrid Fiber Coaxial) 망은 상/하향이 비대칭 구조이며, 하향속도에 비해 상향속도가 1/10 수준이어서 상향 트래픽이 과다하게 생성될 경우 인터넷속도 지연이 발생한다. 지연에 민감한 VoIP 서비스의 품질보장 방안으로는, DOCSIS(Data Over Cable System Interface Specification) 1.1 기반의 상향 스케쥴링 기능을 이 용한 VoCM(Voice Over Cable Modem)이 있다. 그러나 별도의 VoCM을 사용해야 하며 아날로그 전화기를 사용해 IP 기반의 VoIP 단말을 사용할 수 없다는 단점이 있다. 일반 CM(Cable Modem)에 DOCSIS 1.1 Config File을 이용하여 VoIP 품질을 보장할 경우 별도의 트래픽 대역을 항상 점유해야 하는 단점이 있다. 이에, 본 논문에서는 효율적 대역폭 이용과 단말장비에 종속적이지 않은 방안을 제안하고 일반 CM을 통한 유무선 환경하에서 Dynamic QoS(Quality Of Service)를 제공할 수 있는 PCMM(Packet Cable MultiMedia) 적용 방안 및 시험결과에 대해 고찰하고자 한다.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1
• /
• pp.58-68
• /
• 2005

In this paper, we propose a scheme to improve discriminative property in the feature compensation method for robust speech recognition under noisy environments. The estimation of noisy speech model used in existing feature compensation methods do not guarantee the computation of posterior probabilities which discriminate reliably among the Gaussian components. Estimation of Posterior probabilities is a crucial step in determining the discriminative factor of the Gaussian models, which in turn determines the intelligibility of the restored speech signals. The proposed scheme employs minimum classification error (MCE) training for estimating the parameters of the noisy speech model. For applying the MCE training, we propose to identify and determine the 'competing components' that are expected to affect the discriminative ability. The proposed method is applied to feature compensation based on parallel combined mixture model (PCMM). The performance is examined over Aurora 2.0 database and over the speech recorded inside a car during real driving conditions. The experimental results show improved recognition performance in both simulated environments and real-life conditions. The result verifies the effectiveness of the proposed scheme for increasing the performance of robust speech recognition systems.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.6
• /
• pp.872-877
• /
• 2015

The Permanent Magnet (PM) machine used at speed control using field-weakening control method. But the field-weakening current, which reduces the field flux for high speeds, causes significant copper and core losses. Therefore, this paper deals with the PM performance evaluations in a pole changing memory motor (PCMM). The PCMM can change the number of magnetic poles and produce two types of torque. When the motor operates with eight poles, it produces a magnetic torque at low rotational speeds. When the motor changes to four poles, it produces both magnetic torque and reluctance torque at high speeds. The paper explain the principle and basic characteristics of the motor by using a finite element method magnetic-field analysis, which consists of a PM magnetized by a pulse d-axis current of the armature winding. The results of our experiment show that the proposed motor reduces core loss by 10% and 55% under no-load and load conditions, and doubles the speed range of the motor.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1137-1138
• /
• 2011

This paper deals with the PM performance evaluations in a pole changing memory motor (PCMM) using a coupled transient finite element method (FEM) and Preisach modeling, which is presented to analyze the magnetic characteristics of permanent magnets. The focus of this paper is the characteristics evaluation relative to magnetizing direction and the pole number of machine on re-, demagnetization condition in a pole changing memory motor.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.5
• /
• pp.965-970
• /
• 2011

This paper deals with the PM performance evaluations in a pole changing memory motor (PCMM) using a coupled transient finite element method (FEM) and Preisach modeling, which is presented to analyze the magnetic characteristics of permanent magnets. The focus of this paper is the characteristics evaluation relative to magnetizing direction and the pole number of machine on re-demagnetization condition in a pole changing memory motor.

• Journal of Magnetics
• /
• v.16 no.4
• /
• pp.386-390
• /
• 2011

This paper deals with the magnetic equivalent circuit modeling and permanent magnet (PM) performance evaluations of a pole changing memory motor (PCMM). We use a coupled transient finite element method (FEM) and Preisach modeling, which is presented to analyze the magnetic characteristics of the permanent magnets. The focus of this paper is on the evaluation of characteristics such as the magnetizing direction and the pole number of the machine under re- and de-magnetization conditions.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.750_751
• /
• 2009

This paper deals with the PM performance evaluations in a pole changing memory motor (PCMM) using a coupled transient finite element method (FEM) and Preisach modeling, which is presented to analyze the magnetic characteristics of permanent magnets. The focus of this paper is the dynamic characteristics evaluation relative to magnetizing direction and the pole number of machine on redemagnetization condition in a pole changing memory motor

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.892-893
• /
• 2015

This paper deals with a characteristic that varies the number of magnetic pole in permanent magnet (PM) motor in order to reduce energy consumption. The pole changing memory motor (PCMM) can change the number of magnetic poles and produce two types of torque. When the motor operates with eight poles, it produces a magnetic torque at low rotational speeds. When the motor changes to four poles, it produces both magnetic torque and reluctance torque at high speeds. The paper explain the principle and basic characteristics of the motor by using a finite element method magnetic-field analysis, which consists of a PM magnetized by a pulse d-axis current of the armature winding. The results of our experiment show that the proposed motor reduces core loss by 10% and 55% under no-load and load conditions, and doubles the speed range of the motor.

• Journal of the Korean GEO-environmental Society
• /
• v.19 no.11
• /
• pp.5-14
• /
• 2018

Worldwide, soil compaction work is one of the most important activities that are carried out on civil engineering works sites. Compaction work, particularly in the area of road construction, is considered to be important, as poor compaction work is closely related with poor construction even after a construction is complete. Currently, the plate bearing test or the sand cone method relative to the unit weight of soil test are commonly used to measure the degree of compaction, but as these require a great deal of time, equipment and manpower, it is difficult to secure economic efficiency. The method that is used to measure the degree of compaction according to the penetration depth achieved by free fall objects through gravity is the Free-Fall Penetration Test (FFPT), which uses a so-called "portable compaction measuring meter (PCMM)." In this study, the degree of compaction was measured and a penetration depth graph was developed after the field test using the portable compaction measuring meter. The coefficient of determination was 0.963 at a drop height of 10 cm, showing the highest level of accuracy. Both horizontal axis and longitudinal axis were developed in a decimal form of graph, and the range of allowable error was ${\pm}1.28mm$ based on the penetration depth. The portable compaction measuring meter makes it possible to measure the degree of compaction simply, quickly and accurately in the field, which will ensure economic efficiency and facilitate the process management.