• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.381-388
• /
• 2003

This paper presents a method of giving weights to garbage class clustering and Filler model to improve performance of keyword spotting system and a time-saving method of dialogue speech processing system for keyword spotting by calculating keyword transition probability through speech analysis of task domain users. The point of the method is grouping phonemes with phonetic similarities, which is effective in sensing similar phoneme groups rather than individual phonemes, and the paper aims to suggest five groups of phonemes obtained from the analysis of speech sentences in use in Korean morphology and in stock-trading speech processing system. Besides, task-subject Filler model weights are added to the phoneme groups, and keyword transition probability included in consecutive speech sentences is calculated and applied to the system in order to save time for system processing. To evaluate performance of the suggested system, corpus of 4,970 sentences was built to be used in task domains and a test was conducted with subjects of five people in their twenties and thirties. As a result, FOM with the weights on proposed five phoneme groups accounts for 85%, which has better performance than seven phoneme groups of Yapanel [1] with 88.5% and a little bit poorer performance than LVCSR with 89.8%. Even in calculation time, FOM reaches 0.70 seconds than 0.72 of seven phoneme groups. Lastly, it is also confirmed in a time-saving test that time is saved by 0.04 to 0.07 seconds when keyword transition probability is applied.

• Korean Journal of Weed Science
• /
• v.30 no.2
• /
• pp.153-163
• /
• 2010

This study was carried out to establish an improved bioassay system, whole-plant bioassay which is more effective in developing natural herbicides for foliar treatment such as herbicidal essential oils. Two bioassay systems using four weed species (Echinochloa crus-galli, Digitaria sanguinalis, Aeschynomene indica, and Abutilon theophrasti), spraying method and spotting method, were established. Spraying method is applicable if the amount of test compounds is enough, while spotting method is useful for the small amount of test compounds. The initial application rate was desirable at $2,500{\sim}5,000\;{\mu}g\;mL^{-1}$. Herbicidal activities were higher in the NOP treatment when compared to the Tween 20 treatment. To efficiently evaluate volatile compounds such as essential oils, if the compound-treated pots were incubated in dew chamber for about 10hrs, better results were obtained in the degree and stability of herbicidal responses. When the efficiency of bioassay systems established in this study was compared, the spraying method was minimized four times to the conventional method that has beed used for screening of synthetic compounds in KRICT. On the other hand, in the spotting method, screening for development of a natural herbicides was possible even in level of 1/100 test volume and 1/200 amounts of test compound compared to the spraying method.

• Journal of applied mathematics & informatics
• /
• v.22 no.1_2
• /
• pp.541-547
• /
• 2006

A procedure for investigating the influence of observations in choosing Box-Cox transformation for multivariate data is suggested. It is effective in spotting influential observations. A numerical example is provided for illustration.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.484-486
• /
• 2001

본 논문에서는 의사 2차원 은닉 마르코프 모델의 구조로 생성한 마르코프 체인형 확률모형에 의한 인쇄체문자 이미지의 모델링에 대해 논한다. 이미지 데이터에서 바로 모델을 실시간 생성하며 문자 인식 및 검출에 응용할 수 있다. 실험에 의하면, 이 방법을 통해 특정 낱말이 포함된 문장에서 숫자를 인식, 한글을 검출할 수 있음을 확인하였다.

• The Journal of the Korea Contents Association
• /
• v.12 no.3
• /
• pp.442-448
• /
• 2012

Various studies are being carried out to propose a idea for improvement of traditional markets. First of all, it is needed to analysize the current situation of traditional markets. With the help of Customer Spotting Technique the Tongbok traditional market in Pyungtaek has been studied for the case study. The case study was carried out through surveys which are composed of two steps. The first is on the inquiry of users around Tongbok market. The second inquiry is to residents in Pyungtaek. The results are as following: Tongbok market is able to maintain the competitiveness. The proportion of Tongbok is relevant to 13.6% of the total Pyungtaek market, and is to be assessed as a representative market in Pyungtaek.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.153-157
• /
• 1996

본 논문은 연속 분포 HMM을 사용한 핵심어 추출기법(Keyword Spotting)과 화자 인식에 기반한 음성 다이얼링 및 부서 안내에 관한 것이다. 개발된 시스템은 상대방의 이름, 직책, 존칭 등에 감탄사나 명령어 등이 혼합된 형태의 자연스런 음성 문장으로부터 다이얼링과 안내에 필요한 핵심어를 자동 추출하고 있다. 핵심 단어의 사용에는 자연성을 고려하여 문법적 제약을 최소한으로 두었으며, 각 단어 모델에 대해서는 음소의 갯수 더하기 $3{\sim}4$개의 상태 수와 3개 정도의 mixture component로써 좌우향 모델을, 묵음모델에 대해서는 2개 상태의 ergodic형 모델을 구성하였다. 인식에 있어서는 프레임 동기 One-Pass 비터비 알고리즘과 beam pruning을 채택하였으며, 인식에 사용된 어휘는 36개의 성명, 8개의 직위 및 존칭, 5개 정도의 호출어, 부탁을 나타내는 동사 및 그 활용이 10개 정도이다. 약 $3{\sim}6$개 정도의 단어로 구성된 문장을 실시간($1{\sim}3$초이내)에 인식하고, 약 98% 정도의 핵심어 인식 성능을 나타내고 있다.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.100-106
• /
• 2014

URI spotting (탐지) 문제는 텍스트에 있는 단어열 중에서 URI로 대표되는 개체(entity)에 해당되는 것을 탐지하는 것이다. 이 문제는 두 개의 작은 문제를 순차적으로 해결하는 과제이다. 즉, 첫째는 어느 단어열이 URI에 해당하는 개체인가를 인식하는 것이고, 둘째는 개체 중의성 해소 문제로서 파악된 개체가 복수의 URI에 해당할 수 있는 의미적 모호성이 있을 때 그 URI중 하나를 선택하여 모호성을 해소하는 것이다. 이 논문은 디비피디아 URI를 대상으로 한다. URI 탐지 문제는 개체명 인식 문제와 비슷하나, URI(예를 들어 디비피디아 URI, 즉 Wikipedia 등재어)에 매핑될 수 있는 개체로 한정되므로 일반적인 개체명 인식 문제에서 단어열의 품사열이 기계학습의 자질로 들어가는 방법론과는 다른 자질을 사용할 수 있다. 이 논문에서는 한국어 텍스트를 대상으로 한국어 디비피디아 URI 탐지문제로서 SVM을 이용한 개체경계 인식 방법을 제시하여, 일반적 개체명 인식에서 나타나는 품사태거의 오류파급효과를 없애고자 한다. 또한 개체중의성 해소 문제는 의미모호성이 주변 문장들의 토픽에 따라 달라지므로, LDA를 활용하며 이를 영어 디비피디아 URI탐지에서 쓰인 방법들과 비교한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.384-386
• /
• 1998

The use of hand gesture provides an attractive alternative to cumbersome interface devices for human-computer interaction(HCI). Many methods hand gesture recognition using visual analysis have been proposed such as syntactical analysis, neural network(NN), Hidden Markov Model(HMM) and so on. In our research, a HMMs is proposed for alphabetical hand gesture recognition. In the preprocessing stage, the proposed approach consists of three different procedures for hand localization, hand tracking and gesture spotting. The hand location procedure detects the candidated regions on the basis of skin-color and motion in an image by using a color histogram matching and time-varying edge difference techniques. The hand tracking algorithm finds the centroid of a moving hand region, connect those centroids, and thus, produces a trajectory. The spotting a feature database, the proposed approach use the mesh feature code for codebook of HMM. In our experiments, 1300 alphabetical and 1300 untrained gestures are used for training and testing, respectively. Those experimental results demonstrate that the proposed approach yields a higher and satisfying recognition rate for the images with different sizes, shapes and skew angles.

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.774-776
• /
• 2024

The effective implementation of advanced speech recognition (ASR) systems necessitates the deployment of sophisticated keyword spotting models that are both responsive and resource-efficient. The initial local detection of user interactions is crucial as it allows for the selective transmission of audio data to cloud services, thereby reducing operational costs and mitigating privacy risks associated with continuous data streaming. In this paper, we address these needs and propose utilizing the Whisper-Tiny model with fine-tuning process to specifically recognize keywords from google speech dataset which includes 65000 audio clips of keyword commands. By adapting the model's encoder and appending a lightweight classification head, we ensure that it operates within the limited resource constraints of local devices. The proposed model achieves the notable test accuracy of 92.94%. This architecture demonstrates the efficiency as on-device model with stringent resources leading to enhanced accessibility in everyday speech recognition applications.