• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.1
• /
• pp.25-31
• /
• 2014

Korean grammar checkers typically detect context-dependent errors by employing heuristic rules; these rules are formulated by language experts and consisted of lexical items. Such grammar checkers, unfortunately, show low recall which is detection ratio of errors in the document. In order to resolve this shortcoming, a new error-decision rule-generalization method that utilizes the existing KorLex thesaurus, the Korean version of Princeton WordNet, is proposed. The method extracts noun classes from KorLex and generalizes error-decision rules from them using the Tree Cut Model and information-theory-based MDL (minimum description length).

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.23-27
• /
• 2003

Recently attempts to we the syllable as the recognition unit to enhance performance in continuous speech recognition hate been reported. However, syllables are worse in their trainability than phones and the former have a disadvantage in that contort-dependent modeling is difficult across the syllable boundary since the number of models is much larger for syllables than for phones. In this paper, we propose a method to enhance the trainability for the syllables in Korean and phoneme-context dependent syllable modeling across the syllable boundary. An experiment in which the proposed method is applied to word recognition shows average 46.23% error reduction in comparison with the common syllable modeling. The right phone dependent syllable model showed 16.7% error reduction compared with a triphone model.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.4
• /
• pp.159-165
• /
• 2007

In this paper, we propose a new pre-selection of candidate units that is suitable for the unit selection based Japanese TTS system. General pre-selection method performed by calculating a context-dependent cost within IP (Intonation Phrase). Different from other languages, however. Japanese has an accent represented as the height of a relative pitch, and several words form a single accentual phrase. Also. the prosody in Japanese changes in accentual phrase units. By reflecting such prosodic change in pre-selection. the qualify of synthesized speech can be improved. Furthermore, by calculating a context-dependent cost within accentual phrase, synthesis speed can be improved than calculating within intonation phrase. The proposed method defines AP. analyzes AP in context and performs pre-selection using accentual phrase matching which calculates CCL (connected context length) of the Phoneme's candidates that should be synthesized in each accentual phrase. The baseline system used in the proposed method is VoiceText, which is a synthesizer of Voiceware. Evaluations were made on perceptual error (intonation error, concatenation mismatch error) and synthesis time. Experimental result showed that the proposed method improved the qualify of synthesized speech. as well as shortened the synthesis time.

• MALSORI
• /
• v.68
• /
• pp.33-47
• /
• 2008

In this paper, we propose a hybrid acoustic and pronunciation model adaptation method based on context dependency for Korean-English speech recognition. The proposed method is performed as follows. First, in order to derive pronunciation variant rules, an n-best phoneme sequence is obtained by phone recognition. Second, we decompose each rule into a context independent (CI) or a context dependent (CD) one. To this end, it is assumed that a different phoneme structure between Korean and English makes CI pronunciation variabilities while coarticulation effects are related to CD pronunciation variabilities. Finally, we perform an acoustic model adaptation and a pronunciation model adaptation for CI and CD pronunciation variabilities, respectively. It is shown from the Korean-English speech recognition experiments that the average word error rate (WER) is decreased by 36.0% when compared to the baseline that does not include any adaptation. In addition, the proposed method has a lower average WER than either the acoustic model adaptation or the pronunciation model adaptation.

• The KIPS Transactions:PartB
• /
• v.18B no.6
• /
• pp.405-414
• /
• 2011

Korean grammar checkers typically detect context-dependent errors by employing heuristic rules that are manually formulated by a language expert. These rules are appended each time a new error pattern is detected. However, such grammar checkers are not consistent. In order to resolve this shortcoming, we propose new method for generalizing error decision rules to detect the above errors. For this purpose, we use an existing thesaurus KorLex, which is the Korean version of Princeton WordNet. KorLex has hierarchical word senses for nouns, but does not contain any information about the relationships between cases in a sentence. Through the Tree Cut Model and the MDL(minimum description length) model based on information theory, we extract noun classes from KorLex and generalize error decision rules from these noun classes. In order to verify the accuracy of the new method in an experiment, we extracted nouns used as an object of the four predicates usually confused from a large corpus, and subsequently extracted noun classes from these nouns. We found that the number of error decision rules generalized from these noun classes has decreased to about 64.8%. In conclusion, the precision of our grammar checker exceeds that of conventional ones by 6.2%.

• Bulletin of the Korean Chemical Society
• /
• v.30 no.11
• /
• pp.2717-2722
• /
• 2009

The use of the classification and regression tree (CART) methodology was studied in a quantitative structure-activity relationship (QSAR) context on a data set consisting of the binding affinities of 39 imidazobenzodiazepines for the α1 benzodiazepine receptor. The 3-D structures of these compounds were optimized using HyperChem software with semiempirical AM1 optimization method. After optimization a set of 1481 zero-to three-dimentional descriptors was calculated for each molecule in the data set. The response (dependent variable) in the tree model consisted of the binding affinities of drugs. Three descriptors (two topological and one 3D-Morse descriptors) were applied in the final tree structure to describe the binding affinities. The mean relative error percent for the data set is 3.20%, compared with a previous model with mean relative error percent of 6.63%. To evaluate the predictive power of CART cross validation method was also performed.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.173-179
• /
• 2004

Due to the insufficiency of training data in large vocabulary continuous speech recognition, similar context dependent phones can be clustered by decision trees to share the data. When the decision trees are built and used to predict unseen triphones, a phonetic question set is required. The phonetic question set, which contains categories of the phones with similar co-articulation effects, is usually generated by phonetic or linguistic experts. This knowledge-based approach for generating phonetic question set, however, may reduce the homogeneity of the clusters. Moreover, the experts must adjust the question sets whenever the language or the PLU (phone-like unit) of a recognition system is changed. Therefore, we propose a data-driven method to automatically generate phonetic question set. Since the proposed method generates the phone categories using speech data distribution, it is not dependent on the language or the PLU, and may enhance the homogeneity of the clusters. In large vocabulary speech recognition experiments, the proposed algorithm has been found to reduce the error rate by 14.3%.

• Journal of KIISE:Software and Applications
• /
• v.35 no.6
• /
• pp.386-391
• /
• 2008

Some spoken word errors that violate grammatical or writing rules occurs frequently in communication environments like mobile phone and messenger. These unexpected errors cause a problem in a language processing system for many applications like speech recognition, text-to-speech translation, and so on. In this paper, we proposed and implemented an automatic correction system of ill-formed words and word spacing errors in SMS sentences that has been the major errors of poor accuracy. We experimented three methods of constructing the word correction dictionary and evaluated the results of those methods. They are (1) manual construction of error words from the vocabulary list of ill-formed communication languages, (2) automatic construction of error dictionary from the manually constructed corpus, and (3) context-dependent method of automatic construction of error dictionary.

• Proceedings of the KSPS conference
• /
• 2006.05a
• /
• pp.37-40
• /
• 2006

In this paper, we propose a VQ codebook design of speech recognition feature parameters in order to improve the performance of a distributed speech recognition system. For the context-dependent HMMs, a VQ codebook should be correlated with phonetic distributions in the training data for HMMs. Thus, we focus on a selection method of training data based on phonetic distribution instead of using all the training data for an efficient VQ codebook design. From the speech recognition experiments using the Aurora 4 database, the distributed speech recognition system employing a VQ codebook designed by the proposed method reduced the word error rate (WER) by 10% when compared with that using a VQ codebook trained with the whole training data.

• Journal of the Ergonomics Society of Korea
• /
• v.35 no.4
• /
• pp.237-245
• /
• 2016

Objective: This study aims to introduce the bridge resource management (BRM) training courses implemented in Korea and to analyze their effectiveness in several views. Background: BRM training will be a mandatory course for crew members of ships from 2017. At this stage, it is needed to check if the BRM training courses implemented until now was effective to the Korean maritime safety and to investigate if there are more effective training methods. Method: The effectiveness of BRM training intervention in Korea was compared with that of the other countries, using Kirkpatrick's (1976) training evaluation framework. Kim (2012)'s data on the BRM training effectiveness were re-analyzed in order to check if the effects of BRM training are dependent on the bridge work experience. Results: Many BRM training courses has been opened in Korea. However, the methods to assess BRM training effects used in Korea focused on the survey of subjective satisfaction level, not investigating trainees' attitude and behavior change. On the other hand, the effectiveness of BRM training was higher to the bridge officers with long work experience than with shorter work experience. Conclusion: The contents of BRM training should be changed to effectively apply to the context of the real-world exercise and be differentiated depending on the work experience. Research on the methods to measure the BRM training effectiveness is also more required. Application: The results of this study will aid to develop the BRM training courses for bridge officers of ships in the BRM training institutions.