• Title/Summary/Keyword: word bank

Search Result 41, Processing Time 0.023 seconds

HMM-Based Automatic Speech Recognition using EMG Signal

  • Lee Ki-Seung
    • Journal of Biomedical Engineering Research
    • /
    • v.27 no.3
    • /
    • pp.101-109
    • /
    • 2006
  • It has been known that there is strong relationship between human voices and the movements of the articulatory facial muscles. In this paper, we utilize this knowledge to implement an automatic speech recognition scheme which uses solely surface electromyogram (EMG) signals. The EMG signals were acquired from three articulatory facial muscles. Preliminary, 10 Korean digits were used as recognition variables. The various feature parameters including filter bank outputs, linear predictive coefficients and cepstrum coefficients were evaluated to find the appropriate parameters for EMG-based speech recognition. The sequence of the EMG signals for each word is modelled by a hidden Markov model (HMM) framework. A continuous word recognition approach was investigated in this work. Hence, the model for each word is obtained by concatenating the subword models and the embedded re-estimation techniques were employed in the training stage. The findings indicate that such a system may have a capacity to recognize speech signals with an accuracy of up to 90%, in case when mel-filter bank output was used as the feature parameters for recognition.

Analysis on Timely Refusal to Accept Discrepant Documents in Documentary Credit Transactions -with a special emphasis on Federal Bank Ltd. v. VM Jog Engineering Ltd, Indian Supreme Court Decision- (화환신용장 거래에서 은행의 불일치서류 거절의 적시성에 관한 연구 -Federal Bank Ltd. v. VM Jog Engineering Ltd.의 사건에서의 인도 최고법원의 판결을 중심으로-)

  • Hahn, Jae-Phil
    • Journal of Arbitration Studies
    • /
    • v.16 no.3
    • /
    • pp.161-189
    • /
    • 2006
  • This paper is aiming at analyzing case law of India in relation with reasonable time to make decision whether to accept or to refuse the documents received from the presenter in credit transactions. As specified in UCP, the failure to refuse to accept the documents within a reasonable time precludes the Issuing Bank, Confirming Bank (if any) and Nominated Bank from asserting that they are discrepant. Compliance of the stipulated documents on their face with the terms and conditions of the credit shall be determined by international standard banking practice as reflected in this Articles of UCP 500. The Issuing bank is only to be held responsible for honoring the documents presented by beneficiary through the nominated banks if they are strictly in compliance with terms and conditions of the Credit. As any well experienced banker knows, however, a word-by-word, letter-by-letter correspondence between the documents and the credit terms means a practical impossibility. Thus the notion of reasonable care in conjunction with the doctrine of strict compliance mixed with International Standard Banking Practices has not played a right functional standard for checking the documents as stipulated in the credit and UCP 500. And so the rejection rate is highly estimated at approximately 50% in EU and 40 to 70% according to their geographical locations in the USA. As a result, it can possibly be inferred from this fact that the credit industry would be facing the functional failure as the international trade credit facility, if not supported with motive power as a relevant scheme in UCP 500. It is quite important to note that UCP 500 Article 13(b) which specify the time limit for the banks to notify the presenter their decision not to accept the documents within a reasonable time not to exceed seven banking days following the day of receipt of documents would be the motive engine to improve the negotiability of documents in international trade financial facility.

  • PDF

Word Separation in Handwritten Legal Amounts on Bank Check by Measuring Gap Distance Between Connected Components (연결 성분 간 간격 측정에 의한 필기체 수표 금액 문장에서의 단어 추출)

  • Kim, In-Cheol
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.14 no.1
    • /
    • pp.57-62
    • /
    • 2004
  • We have proposed an efficient method of word separation in a handwritten legal amount on bank check based on the spatial gaps between the connected components. The previous gap measures all suffer from the inherent problem of underestimation or overestimation that causes a deterioration in separation performance. In order to alleviate such burden, we have developed a modified version of each distance measure. Also, 4 class clustering based method of integrating three different types of distance measures has been proposed to compensate effectively the errors in each measure, whereby further improvement in performance of word separation is expected. Through a series of word separation experiments, we found that the modified distance measures show a better performance with over 2 - 3% of the word separation rate than their corresponding original distance measures. In addition, the proposed combining method based on 4-class clustering achieved further improvement by effectively reducing the errors common to two of three distance measures as well as the individual errors.

A pilot implementation of Korean in Database Semantics: focusing on numeral-classifier construction (데이터베이스 의미론을 이용한 한국어 구현 시론: 수사-분류사 구조를 중심으로)

  • Choe, Jae-Woong
    • Korean Journal of Cognitive Science
    • /
    • v.18 no.4
    • /
    • pp.457-483
    • /
    • 2007
  • Database Semantics (DBS) attempts to provide a comprehensive and integrated approach to human communication which seeks theory-implementation transparency. Two key components of DBS are Word bank as a data structure and left-Associative Grammar (LAG) as an algorithm. This study aims to provide a pilot implementation of Korean in DBS. First, it is shown how the three separate modules of grammar in DBS, namely, Hear, Think, and Speak, combine to form an integrated system that simulates a cognitive agent by making use of a simple Korean sentence as an example. Second, we provide a detailed analysis of the structure in Korean that is a characteristic of Korean involving numerals, classifiers, and nouns, thereby illustrating how DBS can be applied to Korean. We also discuss an issue raised in the literature concerning a problem that arises when we try to apply the LAG algorithm to the analysis of head-final language like Korean, and then discuss some possible solution to the problem.

  • PDF

A Segmentation-Based HMM and MLP Hybrid Classifier for English Legal Word Recognition (분할기반 은닉 마르코프 모델과 다층 퍼셉트론 결합 영문수표필기단어 인식시스템)

  • 김계경;김진호;박희주
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.11 no.3
    • /
    • pp.200-207
    • /
    • 2001
  • In this paper, we propose an HMM(Hidden Markov modeJ)-MLP(Multi-layer perceptron) hybrid model for recognizing legal words on the English bank check. We adopt an explicit segmentation-based word level architecture to implement an HMM engine with nonscaled and non-normalized symbol vectors. We also introduce an MLP for implicit segmentation-based word recognition. The final recognition model consists of a hybrid combination of the HMM and MLP with a new hybrid probability measure. The main contributions of this model are a novel design of the segmentation-based variable length HMMs and an efficient method of combining two heterogeneous recognition engines. ExperimenLs have been conducted using the legal word database of CENPARMI with encouraging results.

  • PDF

Text Classification Using Parallel Word-level and Character-level Embeddings in Convolutional Neural Networks

  • Geonu Kim;Jungyeon Jang;Juwon Lee;Kitae Kim;Woonyoung Yeo;Jong Woo Kim
    • Asia pacific journal of information systems
    • /
    • v.29 no.4
    • /
    • pp.771-788
    • /
    • 2019
  • Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naïve Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches.

Performance Improvements for Silence Feature Normalization Method by Using Filter Bank Energy Subtraction (필터 뱅크 에너지 차감을 이용한 묵음 특징 정규화 방법의 성능 향상)

  • Shen, Guanghu;Choi, Sook-Nam;Chung, Hyun-Yeol
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.35 no.7C
    • /
    • pp.604-610
    • /
    • 2010
  • In this paper we proposed FSFN (Filter bank sub-band energy subtraction based CLSFN) method to improve the recognition performance of the existing CLSFN (Cepstral distance and Log-energy based Silence Feature Normalization). The proposed FSFN reduces the energy of noise components in filter bank sub-band domain when extracting the features from speech data. This leads to extract the enhanced cepstral features and thus improves the accuracy of speech/silence classification using the enhanced cepstral features. Therefore, it can be expected to get improved performance comparing with the existing CLSFN. Experimental results conducted on Aurora 2.0 DB showed that our proposed FSFN method improves the averaged word accuracy of 2% comparing with the conventional CLSFN method, and FSFN combined with CMVN (Cepstral Mean and Variance Normalization) also showed the best recognition performance comparing with others.

Spatial Gap Estimation for Word Separation in Handwritten Legal Amounts on BAnk Check (필기체 수표 금액 문장에서의 단어 분리를 위한 공간적 간격 추정)

  • Kim In-cheol;Kim Kyoung-min
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.9 no.5
    • /
    • pp.1096-1101
    • /
    • 2005
  • An efficient method of estimating the spatial gaps between the connected components has been prposed to separatethe individual words from a handwritten legal amount on bank check. Owing to the inherent problem of underestimation or overestimation, the previous gap measures have much difficulty in being applied to the legal amounts that usually include the great shape variability by writer's unconstrained writing style and touching or irregular gaps between words by space limitation. In order to alleviate such burden and improve word separation performance, we have developed a modified version of each distance measure. Through a series of word separation experiments, we found that the modified distance measures show a better performance with over $2-3\%$ of the word separation rate than their corresponding original distance measures.

Comparison of Public and Private Perspectives on Central Bank CBDC - Focusing on Korean Case (중앙은행 CBDC에 대한 공공 및 민간 관점의 인식 비교연구- 한국 사례를 중심으로)

  • Kim, Bong-Kyu;Lee, Won-Boo
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.9
    • /
    • pp.360-371
    • /
    • 2021
  • The advent of virtual currencies has heightened interest in the Central Bank Digital Currency (CBDC) issued by the central bank. Recently, central banks in some countries have already decided to issue CBDCs or are in the test phase. This study will be an opportunity to compare public and private perceptions of central banks and explore various issues related to the introduction of CBDCs in the future through analysis methods of big data.

The Effects of Banking Service Quality on Consumer Satisfaction andPositive Word-of- Mouth: With Special Comparisons according to Genderand Age Groups (은행서비스 질이 소비자만족도 및 긍정적 구전에 미치는 영향 : 성별, 연령집단에 따른 비교)

  • Jeong, Woon-Young;Kim, Young-Seen
    • Journal of the Korean Home Economics Association
    • /
    • v.47 no.1
    • /
    • pp.13-24
    • /
    • 2009
  • The purpose of this study was to examine the effects of banking service quality on consumer satisfaction and positive word-of-mouth. A total of 330 bank consumers were investigated between Sept. 11 and Oct. 11, 2006. After sorting through the data, the responses of 299 consumer ( > 24 yrs old) were used for analysis. SERVPERF, the performance component of the Service Quality scale (SERVQUAL), was used to measure the four dimensions of reliability, responsiveness/empathy, assurance, and tangibles. Responses were partitioned by age and gender. The major findings were as follows; The effect of service quality by SERVPERF on consumer satisfaction and positive word-of-mouth did not differ according to gender. However, positive recommendation in males was directy related to the technical quality evaluate. In females, higher the functional quality evaluate was directly related to higher positive word-of-mouth recommendation. The effect of service quality by SERVPERF on consumer satisfaction was not revealed differently according to age. However, with respect to respondents under the age of 45, tangibles and assurance had a positive relationship with word-of-mouth recommendation. Furthermore, the higher the functional quality evaluate, the higher the level of positive word-of-mouth. Responsiveness/empathy was the most significant factor on positive word-of-mouth recommendation in respondents over the age of 45. In this age group, the higher the technical quality evaluate, the higher the level of positive word-of-mouth recommendation. These results have implications for banking service managers, particularly in improving service quality to increase consumer satisfaction and positive word-of-mouth. Future research is needed to replicate this study using more broad and representative samples in order to test the generalization of these findings.