• 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 Journal of the Acoustical Society of Korea
• /
• v.13 no.5
• /
• pp.24-31
• /
• 1994

In this paper, we study continuous speech recognition of Korean language using acoustic models of word juncture coarticulation. To alleviate the performance degradation due to coarticulation problems, we use context-dependent units that model inter-word transitions in addition to intra-word transitions. In all cases the initial phone of each word has to be specified for each possible final phone of the previous word similarly for the final phone of each word. To improve the robustness of the HMM parameters, the covariance matrix is smoothed. We also use position-dependent units to improve the discriminative power between units. Simulation results show that when the improved models of word juncture coarticulation are used. the recognition performance is considerably improved compared to the baseline system using only intra-word units.

• 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.18 no.8
• /
• pp.3-8
• /
• 1999

Previous variable vocabulary speech recognition systems with context-independent acoustic modeling, could not represent the effect of neighboring phonemes. To solve this problem, we use allophone-based context-dependent acoustic model. This paper describes the method to improve acoustic model of the system effectively. Acoustic model is improved by using allophone clustering technique that uses entropy as a similarity measure and the optimal allophone model is generated by changing the number of allophones. We evaluate performance of the improved system by using Phonetically Optimized Words(POW) DB and PC commands(PC) DB. As a result, the allophone model composed of six hundreds allophones improved the recognition rate by 13% from the original context independent model m POW test DB.

• The KIPS Transactions:PartB
• /
• v.17B no.6
• /
• pp.405-412
• /
• 2010

Previous background generation techniques showed bad performance in complex environments since they used only temporal contexts. To overcome this problem, in this paper, we propose a new background generation method which incorporates spatial as well as temporal contexts of the image. This enabled us to obtain 'clean' background image with no moving objects. In our proposed method, first we divided the sampled frame into m*n blocks in the video sequence and classified each block as either static or non-static. For blocks which are classified as non-static, we used MRF framework to model them in temporal and spatial contexts. MRF framework provides a convenient and consistent way of modeling context-dependent entities such as image pixels and correlated features. Experimental results show that our proposed method is more efficient than the traditional one.

• MALSORI
• /
• v.55
• /
• pp.103-118
• /
• 2005

In this paper, we describe a morpheme-based pronunciation lexicon useful for Korean LVCSR. The phonemic-context-dependent multiple pronunciation lexicon improves the recognition accuracy when cross-morpheme pronunciation variations are distinguished from within-morpheme pronunciation variations. Since adding all possible pronunciation variants to the lexicon increases the lexicon size and confusability between lexical entries, we have developed a lexicon pruning scheme for optimal selection of pronunciation variants to improve the performance of Korean LVCSR. By building a proposed pronunciation lexicon, an absolute reduction of $0.56\%$ in WER from the baseline performance of $27.39\%$ WER is achieved by cross-morpheme pronunciation variations model with a phonemic-context-dependent multiple pronunciation lexicon. On the best performance, an additional reduction of the lexicon size by $5.36\%$ is achieved from the same lexical entries.

• Smart Structures and Systems
• /
• v.19 no.5
• /
• pp.539-551
• /
• 2017

A mathematical model of electro-thermoelasticity has been constructed in the context of a new consideration of heat conduction with memory-dependent derivative. The governing coupled equations with time-delay and kernel function, which can be chosen freely according to the necessity of applications, are applied to several concrete problems. The exact solutions for all fields are obtained in the Laplace transform domain for each problem. According to the numerical results and its graphs, conclusion about the proposed model has been constructed. The predictions of the theory are discussed and compared with dynamic classical coupled theory. The result provides a motivation to investigate conducting thermoelectric viscoelastic materials as a new class of applicable materials.

• 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.

• Journal of Korea Port Economic Association
• /
• v.28 no.1
• /
• pp.53-82
• /
• 2012

The purpose of this paper is to show the clustering trend by using the context-dependent and measure-specific models for 38 Asian ports during 10 years(2001-2009) with 4 inputs and 1 output. The main empirical results of this paper are as follows. First, clustering results by using context-dependent and measure-specific models are same. Second, the most efficient clustering was shown among the Hong Kong, Singapore, Ningbo, Guangzhou, and Kaosiung ports. Third, Port Sultan Qaboos, Jeddah, and Aden ports showed the lowest level clustering. Fourth, ranking order of attractiveness is Guangzhou, Dubai, HongKong, Ningbo, and Shanghai, and the results of progressive scores confirmed that low level ports can increase their efficiency by benchmarking the upper level ports. Fifth, benchmark share showed that Dubai(birth length), and HongKong(port depth, total area, and no. of cranes) have affected the efficiency of the inefficient ports.

• Structural Engineering and Mechanics
• /
• v.90 no.5
• /
• pp.459-466
• /
• 2024

Eringen's nonlocal thermoelasticity theory is used to study wave propagations in a rotating two-temperature thermoelastic half-space with temperature-dependent properties. Using suitable non-dimensional variables, the harmonic wave analysis is used to convert the partial differential equations to ordinary differential equations solving the problem. The modulus of elasticity is given as a linear function of the reference temperature. MATLAB software is used for numerical calculations. Comparisons are carried out with the results in the context of the dual-phase lag model for different values of rotation, a nonlocal parameter, an inclined load, and an empirical material constant. The distributions of physical fields showed that the nonlocal parameter, rotation, and inclined load have great effects. When a nonlocal thermoelastic media is swapped out for a thermoelastic one, this approach still holds true.