• Speech Sciences
• /
• v.8 no.2
• /
• pp.49-59
• /
• 2001

The phoneme segmentation is a very difficult problem in speech sound processing because it has found out segmental algorithm in many kinds of allophone and coarticulation's trees. Thus system configuration for the speech recognition and voice retrieval processing has a complex system structure. To solve it, we discuss a possibility of new segmental algorithm, which is called the minus a thirds one or plus in tripartitioning(삼분손익) of twelve temporament(12 율려), first proposed by Prof. T. S. Han. It is close to oriental and western musical theory. He also has suggested a 3 consonant and 3 vowel phonemes in Hunminjungum(훈민정음) invented by the King Sejong in the 15th century. In this paper, we suggest to newly name it as ortho-phonic phoneme(OPP/정음소), which carries the meaning of 'the absoluteness and independency'. OPP also is acceptable to any other languages, for example IPA. Lastly we know that this algorithm is constantly applicable to the global language and is very useful to construct a voice recognition and retrieval structuring engineering.

• MALSORI
• /
• no.57
• /
• pp.113-122
• /
• 2006

Recently, many studies have been done for speech recognition in noisy environments. Particularly, the Aurora DB has been built as the common database for comparing the various feature extraction schemes. However, in general, the recognition models as well as the features have to be modified for effective noisy speech recognition. As the structure of the HTK is very complex, it is not easy to modify, the recognition engine. In this paper, we implemented a baseline recognizer based on the segmental K-means algorithm whose performance is comparable to the HTK in spite of the simplicity in its implementation.

• Structural Engineering and Mechanics
• /
• v.72 no.4
• /
• pp.503-512
• /
• 2019

The construction of segmental precast concrete bridge is an increase due to its superior performance and economic advantages. This type of bridge is appropriate for spans within 30 to 150 m (100 to 500 ft), known as mega-projects and the design optimization would lead to considerable economic benefits. A box-girder cross section superstructure of balanced cantilever construction method is assessed here. The depth of cross section, (variable along the span linearly), bottom flange thickness, and the count of strands are considered as design variables. The optimum design is characterized by geometry, serviceability, ductility, and ultimate limit states specified by AASHTO. Genetic algorithm (GA) is applied in two fronts: as to the saving in construction cost 8% and as to concrete volume 6%. The sensitivity analysis is run by considering different parameters like span/depth ratio, relation between superstructure cost, span length and concrete compressive strength.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.13 no.2
• /
• pp.15-27
• /
• 2009

The purpose of this study is to investigate the seismic behavior of precast segmental PSC bridge columns. For the analysis of reinforced concrete structures, a computer program named RCAHEST (Reinforced Concrete Analysis in Higher Evaluation System Technology) is used. To represent the interaction between tendon and concrete of a prestressed concrete member, a bonded or unbonded tendon element based on the finite element method is used. A joint element is modified to predict the inelastic behaviors of segmental joints. The solution of the equations of motion is obtained by numerical integration using Hilber-Hughes-Taylor (HHT) algorithm. The proposed numerical method gives a realistic prediction of seismic behavior throughout the input ground motions for numerical examples.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.167-179
• /
• 2002

In this paper, we propose a new acoustic model for characterizing segmental features and an algorithm based upon a general framework of hidden Markov models (HMMs) in order to compensate the weakness of HMM assumptions. The segmental features are represented as a trajectory of observed vector sequences by a polynomial regression function because the single frame feature cannot represent the temporal dynamics of speech signals effectively. To apply the segmental features to pattern classification, we adopted segmental HMM(SHMM) which is known as the effective method to represent the trend of speech signals. SHMM separates observation probability of the given state into extra- and intra-segmental variations that show the long-term and short-term variabilities, respectively. To consider the segmental characteristics in acoustic model, we present segmental-feature HMM(SFHMM) by modifying the SHMM. The SFHMM therefore represents the external- and internal-variation as the observation probability of the trajectory in a given state and trajectory estimation error for the given segment, respectively. We conducted several experiments on the TIMIT database to establish the effectiveness of the proposed method and the characteristics of the segmental features. From the experimental results, we conclude that the proposed method is valuable, if its number of parameters is greater than that of conventional HMM, in the flexible and informative feature representation and the performance improvement.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.12 no.4
• /
• pp.45-54
• /
• 2008

The purpose of this study was to investigate the performance of precast segmental PSC bridge columns with regard to P-delta effects. A model of precast segmental PSC bridge columns was tested under a constant axial load and a cyclically reversed horizontal load. A computer program, RCAHEST(Reinforced Concrete Analysis in Higher Evaluation System Technology), was used for the analysis of reinforced concrete structures. In addition to the material nonlinear properties, an algorithm for the problem of large displacement that may result in additional deformation has been formulated using total Lagrangian formulation. This study documents the testing of precast segmental PSC bridge columns under cyclic loading, and presents conclusions based on the experimental and analytical findings.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.84-88
• /
• 1999

The accurate estimation of segmental duration is crucial for natural-sounding text-to-speech synthesis. For predicting Korean segmental durations, conventional methods utilized phonemic context, part-of-speech context and locational information in prosodic phrase. In this paper, the tonal information of phonemes is employed for more accurate prediction. After defining two non-boundary tones and six boundary tones, we annotated the tonal label on each syllable of 400 sentences. To predict segmental duration using tonal information, we constructed neural networks with a real-valued output node predicting phonemic duration and trained them by backpropagation algorithm. Experimental results showed that the proposed features are effective for predicting Korean segmental durations, and we got 0.863 correlation coefficient of the observed durations and predicted ones.

• Korean Journal of Applied Biomechanics
• /
• v.24 no.4
• /
• pp.375-383
• /
• 2014

The purpose of this study was to assess the inter-segmental trunk motion during which multi-segmental movements of the spinal column was designed to interpret the effect of segmentation on the total measured spine motion. Also it analyzed the relative motion at three types of the spine models in drop landing. A secondary goal was to determine the intrinsic algorithmic errors of spine motion and the usefulness of such an approach as a tool to assess spinal motions. College students in the soccer team were selected the ten males with no history of spine symptoms or injuries. Each subject was given a fifteen minute adaptation period of drop landing on the 30cm height box. Inter-segmental spine motion were collected Vicon Motion Capture System (250 Hz) and synchronized with GRF data (1000 Hz). The result shows that Model III has a more increased range of motion (ROM) than Model I and Model II. And the Lagrange energy has significant difference of at E3 and E4 (p<.05). This study can be concluded that there are differences in the three models of algorithm during the phase of load absorption. Especially, Model III shows proper spine motion for the inter-segmental joint motion with the interaction effects using the seven segments. Model III shows more proper observed values about dynamic equilibrium than Model I & Model II. The findings have shown that the dynamic stability strategy of Model III toward multi-directional spinal motion supports for better function of the inter-segmental motor-control than the Model I and Model II.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.39-42
• /
• 1988

In speech signal processing, it is necessary to estimate exactly the pitch. We propose a new algorithm which uses the correlation coefficient between the original and the repeated segmental waveform in the frame as a parameter in the pitch extraction. The correlation coefficient in the frame reflects the periodic component and the transient ratio of the waveform.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1995.10a
• /
• pp.35-42
• /
• 1995

One of the main objectives of this study is to propose a realistic limit state model for reliability-based safety assessment of precast segmental prestressed concrete box girder bridges, considering 1) combined effects of bending, shear and torsional forces, and 2) the difference between transverse reinforcments of box girder. A improved limit state model is derived from a modified interaction equation compared with the Bruno's equation. A Drectional sampling algorithm is used for reliability analysis of the proposed model.