• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.11-16
• /
• 2024

The fundamental frequency (f0), representing an acoustic measure of vocal fold vibration, serves as an indicator of the speaker's emotional state and language-specific pattern in daily conversations. This study aimed to examine the f0 distribution in an English corpus of spontaneous speech, establishing normative data for American speakers. The corpus involved 40 participants engaging in free discussions on daily activities and personal viewpoints. Using Praat, f0 values were collected filtering outliers after removing nonspeech sounds and interviewer voices. Statistical analyses were performed with R. Results indicated a median f0 value of 145 Hz for all the speakers. The f0 values for all speakers exhibited a right-skewed, pointy distribution within a frequency range of 216 Hz from 75 Hz to 339 Hz. The female f0 range was wider than that of males, with a median of 113 Hz for males and 181 Hz for females. This spontaneous speech corpus provides valuable insights for linguists into f0 variation among individuals or groups in a language. Further research is encouraged to develop analytical and statistical measures for establishing reliable f0 standards for the general population.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2178-2198
• /
• 2024

Graph-based document models have good capabilities to reveal inter-dependencies among unstructured text data. Natural language processing (NLP) systems that use such models as an intermediate representation have shown good performance. This paper proposes a novel fuzzy graph-based document model and to demonstrate its effectiveness by applying fuzzy logic tools for text summarization. The proposed system accepts a text document as input and identifies some of its sentence level features, namely sentence position, sentence length, numerical data, thematic word, proper noun, title feature, upper case feature, and sentence similarity. The fuzzy membership value of each feature is computed from the sentences. We also propose a novel algorithm to construct the fuzzy graph as an intermediate representation of the input document. The Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metric is used to evaluate the model. The evaluation based on different quality metrics was also performed to verify the effectiveness of the model. The ANOVA test confirms the hypothesis that the proposed model improves the summarizer performance by 10% when compared with the state-of-the-art summarizers employing alternate intermediate representations for the input text.

• Language Facts and Perspectives
• /
• v.48
• /
• pp.195-227
• /
• 2019

Building upon the state-of-the-art deep learning techniques, the present study classifies the texts written by Korean EFL learners and English native speakers and thereby demonstrates how the two types of texts differ from each other. To this end, the current work makes use of the Yonsei English Learner Corpus (YELC) and Gacheon Learner Corpus (GLC) as the L2 data, and Corpus of Contemporary American English (COCA) as the L1 data. Utilizing the sentence classification methods, the current work implements a system to differentiate the two types of texts, the accuracy of which is about 94%. This indicates that the deep leaning-based system is capable of identifying the well-formedness and felicities of the texts written by Korean EFL learners. Nonetheless, the system-based judgments do not overlap with human judgments largely because the deep learning model exclusively focuses on sequence of words. The present study provides a further analysis to see how the two types of judgments differ with respect to grammatical errors (e.g., word order, voice, etc.) and felicity errors (e.g., semantic prosody, the position of adverbs, etc.).

• Journal of the Korea Computer Industry Society
• /
• v.4 no.12
• /
• pp.901-910
• /
• 2003

Generally, most commercial retrieval engines adopt boolean query as user's query type. Although boolean query is useful to retrieval engines that need fast retrieval, it is not easy for user to express his demands with boolean operators. So, many researches have been studied for decades about information retrieval systems using natural language query that is convenient for user. To retrieve documents that are suitable for user's demands, they have to express their demands correctly, So, this thesis proposes interactive query process agent using natural language. This agent expresses demands concrete through gradual interaction with user, When users input a natural language Query, this agent analyzes the query and generates boolean query by selecting proper keyword and feedbacks the state of the keyword selected. If the keyword is a synonymy or a polysemy, the agent expands or limits the keyword through interaction with user. It makes user express demands more concrete and improve system performance. So, this agent can improve the precision of Information Retrieval.

• Journal of KIISE:Software and Applications
• /
• v.27 no.1
• /
• pp.1-12
• /
• 2000

Model checking is a formal verification technique which checks the consistency between a requirement specification and a behavior model of the system by explorating the state space of the model. We apply model checking to the formal verification of the concurrent object-oriented system, using an existing model checker SPIN which has been successful in verifying concurrent systems. First, we propose an Actor-based modeling language, called APromela, by extending the modeling language Promela which is a modeling language supported in SPIN. APromela supports not only all the primitives of Promela, but additional primitives needed to model concurrent object-oriented systems, such as class definition, object instantiation, message send, and synchronization.Second, we provide translation rules for mapping APromela's such modeling primitives to Promela's. As an application of APromela, we suggest a verification method for UML models. By giving an example of specification, translation, and verification, we also demonstrate the applicability of our proposed approach, and discuss the limitations and further research issues.

• Journal of The Korean Association of Information Education
• /
• v.23 no.4
• /
• pp.303-314
• /
• 2019

Since 2019, the informatics education is being conducted for elementary school 5th, 6th grade students through the curriculum revised 2015. But, informatics education is implemented from the lower grades of elementary school in many countries. The purpose of this study was to suggest the direction in the choice of programming language considering characteristics for lower grades student. In order to achieve the goal, evaluation criteria were developed considering the development characteristics of lower grades and necessary elements of educational programming language. The results of analyzing the usability of the two languages based on the criterion are as follows. First, Viscuit can be used to consider the expressive power of students with lower school age or to learn algorithms without learning about programming concepts. Second, ScratchJr is easy to learn the concept of algorithm and programming. This study is meaningful in that has presented implications considering the developmental state of the students in preparation for rhe programming education.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.437-446
• /
• 2022

Text classification task from Natural Language Processing (NLP) combined with state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms as the core engine is widely used to detect and classify voice phishing call transcripts. While numerous studies on the classification of voice phishing call transcripts are being conducted and demonstrated good performances, with the increase of non-face-to-face financial transactions, there is still the need for improvement using the latest NLP technologies. This paper conducts a benchmarking of Korean voice phishing detection performances of the pre-trained Korean language model KoBERT, against multiple other SOTA algorithms based on the classification of related transcripts from the labeled Korean voice phishing dataset called KorCCVi. The results of the experiments reveal that the classification accuracy on a test set of the KoBERT model outperforms the performances of all other models with an accuracy score of 99.60%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.1009-1017
• /
• 2022

Log data has been used as a basis in understanding and deciding the main functions and state of information systems. It has also been used as an important input for the various applications in cybersecurity. It is an essential part to get necessary information from log data, to make a decision with the information, and to take a suitable countermeasure according to the information for protecting and operating systems in stability and reliability, but due to the explosive increase of various types and amounts of log, it is quite challenging to effectively and efficiently deal with the problem using existing tools. Therefore, this study has suggested a multiclass classification of the security severity level of multi-source event log using machine learning based on natural language processing. The experimental results with the training and test samples of 472,972 show that our approach has archived the accuracy of 99.59%.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.334-342
• /
• 2022

Nowadays, as we can notice on social media, most users choose to use more than one language in their online postings. Thus, social media analytics needs reviewing as code-switching analytics instead of traditional analytics. This paper aims to present evidence comparable to the accuracy of code-switching analytics techniques in analysing the mood state of social media users. We conducted a systematic literature review (SLR) to study the social media analytics that examined the effectiveness of code-switching analytics techniques. One primary question and three sub-questions have been raised for this purpose. The study investigates the computational models used to detect and measures emotional well-being. The study primarily focuses on online postings text, including the extended text analysis, analysing and predicting using past experiences, and classifying the mood upon analysis. We used thirty-two (32) papers for our evidence synthesis and identified four main task classifications that can be used potentially in code-switching analytics. The tasks include determining analytics algorithms, classification techniques, mood classes, and analytics flow. Results showed that CNN-BiLSTM was the machine learning algorithm that affected code-switching analytics accuracy the most with 83.21%. In addition, the analytics accuracy when using the code-mixing emotion corpus could enhance by about 20% compared to when performing with one language. Our meta-analyses showed that code-mixing emotion corpus was effective in improving the mood analytics accuracy level. This SLR result has pointed to two apparent gaps in the research field: i) lack of studies that focus on Malay-English code-mixing analytics and ii) lack of studies investigating various mood classes via the code-mixing approach.

• 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.