• The Journal of the Acoustical Society of Korea
• /
• v.18 no.3
• /
• pp.3-9
• /
• 1999

This paper presents the study on the rejection capability based on anti-phone modeling for vocabulary independent speech recognition system. The rejection system detects and rejects out-of-vocabulary words which were not included in candidate words which are defined while the speech recognizer is made. The rejection system can be classified into two categories by their implementation methods, keyword spotting method and utterance verification method. The keyword spotting method uses an extra filler model as a candidate word as well as keyword models. The utterance verification method uses the anti-models for each phoneme for the calculation of confidence score after it has constructed the anti-models for all phonemes. We implemented an utterance verification algorithm which can be used for vocabulary independent speech recognizer. We also compared three kinds of means for the calculation of confidence score, and found out that the geometric mean had shown the best result. For the normalization of confidence score, usually Sigmoid function is used. On using it, we compared the effect of the weight constant for Sigmoid function and determined the optimal value. And we compared the effects of the size of cohort set, the results showed that the larger set gave the better results. And finally we found out optimal confidence score threshold value. In case of using the threshold value, the overall recognition rate including rejection errors was about 76%. This results are going to be adapted for stock information system based on speech recognizer which is currently provided as an experimental service by Korea Telecom.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1471-1479
• /
• 2008

In this paper, we propose a technique to improve Out-Of-Vocabulary(OOV) rejection algorithms in variable vocabulary recognition system which is much used in ASR(Automatic Speech Recognition). The rejection system can be classified into two categories by their implementation method, keyword spotting method and utterance verification method. The utterance verification method uses the likelihood ratio of each phoneme Viterbi score relative to anti-phoneme score for deciding OOV. In this paper, we add speaker verification system before utterance verification and calculate an speaker verification probability. The obtained speaker verification probability is applied for determining the proposed variable-confidence threshold. Using the proposed method, we achieve the significant performance improvement; CA(Correctly Accepted for keyword) 94.23%, CR(Correctly Rejected for out-of-vocabulary) 95.11% in office environment, and CA 91.14%, CR 92.74% in noisy environment.

• Korean Journal of Applied Biomechanics
• /
• v.17 no.1
• /
• pp.175-184
• /
• 2007

The first purpose of this study was to compare kinematic variables during spinning motion with or without upper extremity and identify the most effective spinning method. The second purpose of this study was to compare functional difference between novice and elite dancers with the term of training. Ten experienced female dancers and ten novices were recruited as subjects for this study. Elite group was asked to perform turn motion with three types of upper extremity. Novice group has taken training of spotting technique for five weeks. Four Falcon HiRES cameras were used to analyze kinematic variables including head angular velocity and CG displacement during spinning. These data were sampled before training, after 3-week, and 5-week of training. Eight different events in two consecutive turns were defined for statistical comparison. One-way ANOVA was performed to compare among the kinematics of turning motion with three types of upper extremity. Independent t-test also used to compare kinematics between elite and novice at three different length of training. As results, spinning with both arm increased angular velocity and stability compared to the turning motion with one arm or with arm strapped and found out that the turn with both arm was the most effective way of spin. Also, for novice dancers, three weeks of training were needed to complete spinning motion.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.380-386
• /
• 2002

Conventional post-processing as like confidence measure (CM) proposed by Rahim calculates phones' CM using the likelihood between phoneme model and anti-model, and then word's CM is obtained by averaging phone-level CMs[1]. In conventional method, CMs of some specific keywords are tory low and they are usually rejected. The reason is that statistics of phone-level CMs are not consistent. In other words, phone-level CMs have different probability density functions (pdf) for each phone, especially sri-phone. To overcome this problem, in this paper, we propose normalized confidence measure. Our approach is to transform CM pdf of each tri-phone to the same pdf under the assumption that CM pdfs are Gaussian. For evaluating our method we use common keyword spotting system. In that system context-dependent HMM models are used for modeling keyword utterance and contort-independent HMM models are applied to non-keyword utterance. The experiment results show that the proposed NCM reduced FAR (false alarm rate) from 0.44 to 0.33 FA/KW/HR (false alarm/keyword/hour) when MDR is about 8%. It achieves 25% improvement of FAR.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.7
• /
• pp.632-640
• /
• 2002

In this paper, we proposed ACM (Anti-filler confidence measure) to compensate shortcoming of conventional RLJ-CM (RLJ-CM) and NCM (normalized CM), and integrated proposed ACM and conventional NCM using HCM (hybrid CM). Proposed ACM analyzes that FA (false acceptance) happens by the construction method of anti-phone model, and presumed phoneme sequence in actuality using phoneme recognizer to compensate this. We defined this as anti-phone model and used in confidence measure calculation. Analyzing feature of two confidences measure, conventional NCM shows good performance to FR (false rejection) and proposed ACM shows good performance in FA. This shows that feature of each other are complementary. Use these feature, we integrated two confidence measures using weighting vector α And defined this as HCM. In MDR (missed detection rate) 10% neighborhood, HCM is 0.219 FA/KW/HR (false alarm/keyword/hour). This is that Performance improves 22% than used conventional NCM individually.

• MALSORI
• /
• no.46
• /
• pp.103-115
• /
• 2003

In this paper, we proposed Background Model Set algorithm used in the speaker verification to improve calculating confidence measure(CM) in speech recognition. CM is to display relative likelihood between recognized models and antiphone models. In previous method calculating of CM, we calculated probability and standard deviation using all phonemes in composition of antiphone models. At this process, antiphone CM brought bad recognition result. Also, recognition time increases. In order to solve this problem, we studied about method to reconstitute average and standard deviation using BMS algorithm in CM calculation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.516-520
• /
• 2007

This paper presents a intuitive, simple and easy smart home TV remote control system using the hand gesture recognition. Hand candidate regions are detected by cascading policy of the part of human anatomy on the disparity map image, Exact hand region is extracted by the graph-cuts algorithm using the skin color information. Hand postures are represented by shape features which are extracted by a simple shape extraction method. We use the forward spotting accumulative HMMs for a smart home TV remote control system. Experimental results show that the proposed system has a good recognition rate of 97.33 % for TV remote control in real-time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2824-2838
• /
• 2013

There has been a lot of attention paid recently to analyze dynamic human gestures that vary over time. Most attention to dynamic gestures concerns with spatio-temporal features, as compared to analyzing each frame of gestures separately. For accurate dynamic gesture recognition, motion feature extraction algorithms need to find representative features that uniquely identify time-varying gestures. This paper proposes a new feature-extraction algorithm using temporal self-similarity based on a hierarchical human model. Because a conventional temporal self-similarity method computes a whole movement among the continuous frames, the conventional temporal self-similarity method cannot recognize different gestures with the same amount of movement. The proposed model-based temporal self-similarity method groups body parts of a hierarchical model into several sets and calculates movements for each set. While recognition results can depend on how the sets are made, the best way to find optimal sets is to separate frequently used body parts from less-used body parts. Then, we apply a multiclass support vector machine whose optimization algorithm is based on structural support vector machines. In this paper, the effectiveness of the proposed feature extraction algorithm is demonstrated in an application for taebo gesture recognition. We show that the model-based temporal self-similarity method can overcome the shortcomings of the conventional temporal self-similarity method and the recognition results of the model-based method are superior to that of the conventional method.

• Journal of Power Electronics
• /
• v.12 no.6
• /
• pp.869-877
• /
• 2012

This paper presents a current-balancing circuit for security lights that uses parallel-connected LEDs. The parallel connection of LEDs causes current differences between the LED strings because of characteristic deviations. These differences can reduce the lifespan of a particular point of LEDs by thermal spotting. They can also cause non-uniform luminance of the lighting device. Among the different methods for solving these problems, the method using current-balancing transformers makes it easy to compensate for current differences and it has a simple circuitry. However, while the balancing transformer has been applied to AC light sources, LEDs operate on a DC source, so the driving circuitry and the design method have to be changed and their performances must be verified. Thus in this paper, a design method of the balancing transformer network and the driving circuitry for LEDs is proposed. The proposed design method could have a smaller size than the conventional design method. The proposed circuitry is applied to three types of 100-watt LED security lights, which use different LEDs. Experimental results are presented to verify the performance of the designed driving circuits.

• Journal of Power System Engineering
• /
• v.15 no.5
• /
• pp.22-29
• /
• 2011

In this study, the damage mechanism of large scale steam turbine due to water induction was analyzed and recovery characteristics were reviewed. A turbine consists of the rotating rotor and the stationary casing, and the clearance between them is very small for the efficiency enhancement. If water induction, while relatively cold steam or water is introduced into turbine, occurs, the considerable humping is caused at the casing near the initial water induction point and that induces the rubbing between rotor and casing. Finally, it leads to the catastrophic failure. Bowed rotor has the different characteristics in the recovery depending on damage degree. The elastic deformation due to light rubbing is recovered by turning the rotor with 3 rpm under normal operation condition, but most plastic deformation due to rubbing deforms the local microstructure and that results in permanent deformation which could not be recovered under normal operation condition. Bowed rotor has diverse characteristics depending on the recovery method, and the method is empirical and needs the cutting edge technology. Careful recovery treatment of the rotor will eliminate the risks and secure the high quality rotor similar to new rotor. If any critical error is made during the recovery, the rotor would not be recovered permanently and it should be scrapped.