• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.155-163
• /
• 2009

In text-to-speech systems, the conversion of text into prosodic parameters is necessarily composed of three steps. These are the placement of prosodic boundaries. the determination of segmental durations, and the specification of fundamental frequency contours. Prosodic boundaries. as the most important and basic parameter. affect the estimation of durations and fundamental frequency. Break prediction is an important step in text-to-speech systems as break indices (BIs) have a great influence on how to correctly represent prosodic phrase boundaries, However. an accurate prediction is difficult since BIs are often chosen according to the meaning of a sentence or the reading style of the speaker. In Japanese, the prediction of an accentual phrase boundary (APB) and major phrase boundary (MPB) is particularly difficult. Thus, this paper presents a method to complement the prediction errors of an APB and MPB. First, we define a subtle BI in which it is difficult to decide between an APB and MPB clearly as a variable break (VB), and an explicit BI as a fixed break (FB). The VB is chosen using the classification and regression tree, and multiple prosodic targets in relation to the pith and duration are then generated. Finally. unit-selection is conducted using multiple prosodic targets. In the MOS test result. the original speech scored a 4,99. while proposed method scored a 4.25 and conventional method scored a 4.01. The experimental results show that the proposed method improves the naturalness of synthesized speech.

• Journal of Korea Water Resources Association
• /
• v.42 no.6
• /
• pp.457-464
• /
• 2009

This paper proposes methodologies for analyzing the accuracy of the proportional hazards model in predicting consecutive break times of water mains and estimating the time interval for economical water main replacement. By using the survival functions that are based on the proportional hazards models a criterion for the prediction of the consecutive pipe breaks is determined so that the prediction errors are minimized. The criterion to predict pipe break times are determined as the survival probability of 0.70 and only the models for the third through the seventh break are analyzed to be reliable for predicting break times for the case study pipes. Subsequently, the criterion and the estimated lower and upper bound survival functions of consecutive breaks are used in predicting the lower and upper bounds of the 95% confidence interval of future break times of an example water main. Two General Pipe Break Prediction Models(GPBMs) are estimated for an example pipe using the two series of recorded and predicted lower and upper bound break times. The threshold break rate is coupled with the two GPBMs and solved for time to obtain the economical replacement time interval.

• Journal of KIISE:Software and Applications
• /
• v.37 no.11
• /
• pp.837-844
• /
• 2010

Prediction of the prosodic phrase boundary is one of the most important natural language processing tasks. We propose, for the natural prediction of the Korean prosodic phrase boundary, a statistical approach incorporating efficient learning features. These new features reflect the factors that affect generation of the prosodic phrase boundary better than existing learning features. Notably, moreover, such learning features, extracted according to the hand-crafted prosodic phrase boundary prediction rule, impart higher accuracy. We developed a statistical model for Korean prosodic phrase boundaries based on the proposed new features. The results were 86.63% accuracy for three levels (major break, minor break, no break) and 81.14% accuracy for six levels (major break with falling tone/rising tone, minor break with falling tone/rising tone/middle tone, no break).

• Journal of Korean Society of Water and Wastewater
• /
• v.16 no.6
• /
• pp.710-716
• /
• 2002

A General Pipe Break Prediction Model that incorporates linear and exponential models in its form is developed. The model is capable of fitting pipe break trends that have linear, exponential or in between of linear and exponential trend by using a weighting factor. The weighting factor is adjusted to obtain a best model that minimizes the sum of squared errors of the model. The model essentially plots a best curve (or a line) passing through "cumulative number of pipe breaks" versus "break times since installation of a pipe" data points. Therefore, it prevents over-predicting future number of pipe breaks compared to the conventional exponential model. The optimal replacement time equation is derived by using the Threshold Break Rate equation by Loganathan et al. (2002).

• Korean Journal of Cognitive Science
• /
• v.19 no.1
• /
• pp.89-105
• /
• 2008

In this paper, we suggest a rule-based system for the prediction of natural prosodic phrase breaks from Korean texts. For the implementation of the rule-based system, (1) sentence constituents are sub-categorized according to their syntactic functions, (2) syntactic phrases are recognized using the dependency relations among sub-categorized constituents, (3) rules for predicting prosodic phrase breaks are created. In addition, (4) the length of syntactic phrases and sentences, the position of syntactic phrases in a sentence, sense information of contextual words have been considered as to determine the variable prosodic phrase breaks. Based on these rules and features, we obtained the accuracy over 90% in predicting the position of major break and no break which have high correlation with the syntactic structure of the sentence. As for the overall accuracy in predicting the whole prosodic phrase breaks, the suggested system shows Break_Correct of 87.18% and Juncture Correct of 89.27% which is higher than that of other models.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.8
• /
• pp.403-408
• /
• 2007

In a large corpus-based speech synthesizer, a break, which is a parameter influencing the naturalness and intelligibility, is used as an important feature during a unit selection process. Japanese is a language having intonations, which ate indicated by the relative differences in pitch heights and the APs(Accentual Phrases) are placed according to the changes of the accents while a break occurs on a boundary of the APs. Although a break can be predicted by using J-ToBI(Japanese-Tones and Break Indices), which is a rule-based or statistical approach, it is very difficult to predict a break exactly due to the flexibility. Therefore, in this paper, a method is to conduct a unit search by dividing breaks into two types, such as a fixed break and a flexible break, in order to use the advantages of a large-scale corpus, which includes various types of prosodies. As a result of an experiment, the proposed unit selection method contributed itself to enhance the naturalness of synthesized speeches.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.8
• /
• pp.1446-1450
• /
• 1992

A method of prediction for the fatigue life of surface crack, that is, initial cracks grow and penetrate through the thickness, was presented in the previous study of the authors. Effects of parameters such as the initial crack depth, material factors, etc., for the life were also discussed. However, in the case of adapting the concept of LBB(Leak Before Break), the break fatigue life after the penetration of the thickness must be taken into account. Hence, a method to predict the break fatigue life is presented in this paper. Effects of the parameters for the break fatigue life are discussed and compared with the penetration fatigue life.

• Journal of Korea Water Resources Association
• /
• v.42 no.7
• /
• pp.571-578
• /
• 2009

Levee-break Analysis model is developed to predict the variation of breach width according to time and to estimate inundation area and depth in protected lowland. This Model calculate flood depth using 4 point implicit finite difference method in river channel and analyze breach flow based on physical theory introducing soil transport equation and erosion process. Breach analysis model and channel flood model are combined into Levee-Break Model and this model is applied to actual levee break case. Then, this model can simulate reasonably many levee-break parameters such as river stage, breach width, breach formation and so on. If the applicability of this model is proved through applications to more various actual levee-break cases, the suggested model is expected to do more accurate flood analyses on levee break site.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.7
• /
• pp.17-22
• /
• 1999

In this paper we propose a new mixed method of LDA and tri-tone model to predict Korean prosodic break indices(PBI) for a given utterance. PBI can be used as an important cue of syntactic discontinuity in continuous speech recognition(CSR). The model consists of three steps. At the first step, PBI was predicted with the information of syllable and pause duration through the linear discriminant analysis (LDA) method. At the second step, syllable tone information was used to estimate PBI. In this step we used vector quantization (VQ) for coding the syllable tones and PBI is estimated by tri-tone model. In the last step, two PBI predictors were integrated by a weight factor. The proposed method was tested on 200 literal style spoken sentences. The experimental results showed 72% accuracy.

• MALSORI
• /
• no.62
• /
• pp.69-84
• /
• 2007

Japanese is a language having intonations, which are indicated by the relative differences in pitch heights and the accentual phrases (APs) are placed according to the changes of the accents while a break occurs on a boundary of the APs. Although a break can be predicted by using J-ToBI, which is a rule-based or statistical approach, it is very difficult to predict a break exactly due to the flexibility. Therefore, in this paper, a method which can enhance the quality of synthesized speech by reducing the errors in predicting break indices (BI), are proposed. The method is to use a new definition for the phonetic symbols, which combine the phonetic values of Japanese words with the accents information. Since a stream of defined phonetic symbols includes the information on the changes in intonations, the BI can be easily predicted by dividing the intonation phrase (IP) into several APs. As a result of an experiment, the accuracy of break generations was 98 % and the proposed method contributed itself to enhance the naturalness of synthesized speeches.