• Speech Sciences
• /
• v.9 no.1
• /
• pp.111-135
• /
• 2002

An annotation model of a non-native speech database has been devised, wherein English is the target language and Korean is the native language. The proposed annotation model features overt transcription of predictable linguistic information in native speech by the dictionary entry and several predefined types of error specification found in native language transfer. The proposed model is, in that sense, different from other previously explored annotation models in the literature, most of which are based on native speech. The validity of the newly proposed model is revealed in its consistent annotation of 1) salient linguistic features of English, 2) contrastive linguistic features of English and Korean, 3) actual errors reported in the literature, and 4) the newly collected data in this study. The annotation method in this model adopts the widely accepted conventions, Speech Assessment Methods Phonetic Alphabet (SAMPA) and the TOnes and Break Indices (ToBI). In the proposed annotation model, SAMPA is exclusively employed for segmental transcription and ToBI for prosodic transcription. The annotation of non-native speech is used to assess speaking ability for English as Foreign Language (EFL) learners.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.3
• /
• pp.76-82
• /
• 2010

In this paper, we develop Linguistic Model (LM) based on information granules as a systematic approach to generating fuzzy if-then rules from a given input-output data. The LM introduced by Pedrycz is performed by fuzzy information granulation obtained from Context-based Fuzzy Clustering(CFC). This clustering estimates clusters by preserving the homogeneity of the clustered patterns associated with the input and output data. Although the effectiveness of LM has been demonstrated in the previous works, it needs to improve in the sense of performance. Therefore, we focus on the automatic generation of linguistic contexts, addition of bias term, and the transformed form of consequent parameter to improve both approximation and generalization capability of the conventional LM. The experimental results revealed that the improved LM yielded a better performance in comparison with LM and the conventional works for automobile MPG(miles per gallon) predication and Boston housing data.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.1
• /
• pp.89-97
• /
• 2001

Chen and Chen(FSS, 1993, 159-168) presented a reasonable analytical model of fuzzy closed-loop systems and proposed a method to analyze the stability of fuzzy control by the relational matrix of fuzzy system. Chen, Lu and Chen(IEEE Trans. Syst. Man Cybern., 1995, 881-888) formulated the sufficient and necessary conditions on stability of fuzzy closed-loop control systems. Gang and Chen(FSS, 1996, 27-34) deduced a linguistic relation model of a fuzzy closed loop control system from the linguistic models of the fuzzy controller and the controlled process and discussed the linguistic stability of fuzzy closed loop system by a linguistic relation matrix. In this paper, we study more on their models. Indeed, we prove the existence and uniqueness of equilibrium state $X_e$ in which fuzzy system is stable and give closed form of $X_e$. The same examples in Chen and Chen and Gang and Chen are treated to analyze the stability of fuzzy control systems.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.365-370
• /
• 2023

This paper aims to compare the performance of speech data classification into two groups, adult and elderly, based on the acoustic and linguistic characteristics that change due to aging, such as changes in respiratory patterns, phonation, pitch, frequency, and language expression ability. For acoustic features we used attributes related to the frequency, amplitude, and spectrum of speech voices. As for linguistic features, we extracted hidden state vector representations containing contextual information from the transcription of speech utterances using KoBERT, a Korean pre-trained language model that has shown excellent performance in natural language processing tasks. The classification performance of each model trained based on acoustic and linguistic features was evaluated, and the F1 scores of each model for the two classes, adult and elderly, were examined after address the class imbalance problem by down-sampling. The experimental results showed that using linguistic features provided better performance for classifying adult and elderly than using acoustic features, and even when the class proportions were equal, the classification performance for adult was higher than that for elderly.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1296-1301
• /
• 2004

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision making in complex systems. The fuzzy -neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes learning approach of fuzzy-neural network by immune algorithm. The proposed learning model is presented in an immune based fuzzy-neural network (FNN) form which can handle linguistic knowledge by immune algorithm. The learning algorithm of an immune based FNN is composed of two phases. The first phase used to find the initial membership functions of the fuzzy neural network model. In the second phase, a new immune algorithm based optimization is proposed for tuning of membership functions and structure of the proposed model.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.303-308
• /
• 2004

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision making in complex systems. The fuzzy-neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes learning approach of fuzzy-neural network by immune algorithm. The proposed learning model is presented in an immune based fuzzy-neural network (FNN) form which can handle linguistic knowledge by immune algorithm. The learning algorithm of an immune based FNN is composed of two phases. The first phase used to find the initial membership functions of the fuzzy neural network model. In the second phase, a new immune algorithm based optimization is proposed for tuning of membership functions and structure of the proposed model.

• Korean Journal of Construction Engineering and Management
• /
• v.4 no.1 s.13
• /
• pp.81-89
• /
• 2003

This research suggests the FD-AHP decision making model for Construction Projects which is composed of two main method to prevent a ranking invert situation ; First, to make the consensus of the experts consistent, we utilize Fuzzy-Delphi method to adjust the fuzzy rating of every expert to achive the consensus condition with the fuzzy linguistic presentation. Second, to handle vague linguistic presentation caused by expert's experiences and subjective judgement, we propose Fuzzy-AHP which is able to enhance precision of construction projects decision mating situation. Moreover, with the correlation analysis, we show that the validity of the FD-AHP model under a decision making task specially on where highly demanded expert's experiences and intuition.

• Language and Information
• /
• v.7 no.2
• /
• pp.103-115
• /
• 2003

In recent years, many organizations have been constructing their own large corpora to achieve corpus representativeness. However, there is no reliable guideline as to how large corpus resources should be compiled, especially for Korean corpora. In this study, we have contrived a new statistical model, ARIMA (Autoregressive Integrated Moving Average), for predicting the relationship between linguistic items (the number of types) and corpus size (the number of tokens), overcoming the major flaws of several previous researches on this issue. Finally, we shall illustrate that the ARIMA model presented is valid, accurate and very reliable. We are confident that this study can contribute to solving some inherent problems of corpus linguistics, such as corpus predictability, corpus representativeness and linguistic comprehensiveness.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.125-132
• /
• 2022

Sentence compression is a natural language processing task that generates concise sentences that preserves the important meaning of the original sentence. For grammatically appropriate sentence compression, early studies utilized human-defined linguistic rules. Furthermore, while the sequence-to-sequence models perform well on various natural language processing tasks, such as machine translation, there have been studies that utilize it for sentence compression. However, for the linguistic rule-based studies, all rules have to be defined by human, and for the sequence-to-sequence model based studies require a large amount of parallel data for model training. In order to address these challenges, Deleter, a sentence compression model that leverages a pre-trained language model BERT, is proposed. Because the Deleter utilizes perplexity based score computed over BERT to compress sentences, any linguistic rules and parallel dataset is not required for sentence compression. However, because Deleter compresses sentences only considering perplexity, it does not compress sentences by reflecting the linguistic information of the words in the sentences. Furthermore, since the dataset used for pre-learning BERT are far from compressed sentences, there is a problem that this can lad to incorrect sentence compression. In order to address these problems, this paper proposes a method to quantify the importance of linguistic information and reflect it in perplexity-based sentence scoring. Furthermore, by fine-tuning BERT with a corpus of news articles that often contain proper nouns and often omit the unnecessary modifiers, we allow BERT to measure the perplexity appropriate for sentence compression. The evaluations on the English and Korean dataset confirm that the sentence compression performance of sentence-scoring based models can be improved by utilizing the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.417-423
• /
• 2002

In this paper, we propose intelligent steering control system that apply LIBL(Linguistic Instruction Based Learning) method to steering system of ship and take the place of process that linguistic instruction such as officer s steering instruction is achieved via ableman. We embody ableman s suitable steering manufacturing model using fuzzy inference rule by specific method of study, and apply LIBL method to present suitable meaning element and evaluation rule to steering system of ship, embody intelligent steering gear control system that respond more efficiently on officer s linguistic instruction. We presented evaluation rule to constructed steering manufacturing model based on ableman s experience, and propose rudder angle for steering system, compass bearing arrival time, meaning element of stationary state, and correct ableman manufacturing model rule using fuzzy inference. Also, we apply LIBL method to ship control simulator and confirmed the effectiveness.