• Genomics & Informatics
• /
• v.17 no.2
• /
• pp.21.1-21.6
• /
• 2019

Dependency parsing is often used as a component in many text analysis pipelines. However, performance, especially in specialized domains, suffers from the presence of complex terminology. Our hypothesis is that including named entity annotations can improve the speed and quality of dependency parses. As part of BLAH5, we built a web service delivering improved dependency parses by taking into account named entity annotations obtained by third party services. Our evaluation shows improved results and better speed.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.171-189
• /
• 2022

Online reviews play an essential role in the consumer's purchasing decision-making process, and thus, providing helpful and reliable reviews is essential to consumers. Previous online review helpfulness prediction studies mainly predicted review helpfulness based on the consistency of text and rating information of online reviews. However, there is a limitation in that representation capacity or review text and rating interaction. We propose a CNN-RHP model that effectively learns the interaction between review text and rating information to improve the limitations of previous studies. Multi-channel CNNs were applied to extract the semantic representation of the review text. We also converted rating into independent high-dimensional embedding vectors representing the same dimension as the text vector. The consistency between the review text and the rating information is learned based on element-wise operations between the review text and the star rating vector. To evaluate the performance of the proposed CNN-RHP model in this study, we used online reviews collected from Amazom.com. Experimental results show that the CNN-RHP model indicates excellent performance compared to several benchmark models. The results of this study can provide practical implications when providing services related to review helpfulness on online e-commerce platforms.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.735-743
• /
• 2002

In this paper, we propose three new text-independent speaker identification methods. At first, to exclude the frames not having enough features of speaker's vocal from calculation of the maximum likelihood, we propose the FS(Frame Selection) method. This approach selects the important frames by evaluating the difference between the biggest likelihood and the second in each frame, and uses only the frames in calculating the score of likelihood. Our secondly proposed, called the Hybrid, is a combined version of the FS and WMR(Weighting Model Rank). This method determines the claimed speaker using exponential function weights, instead of likelihood itself, only on the selected frames obtained from the FS method. The last proposed, called MWMR (Modified WMR), considers both original likelihood itself and its relative position, when the claimed speaker is determined. It is different from the WMR that take into account only the relative position of likelihood. Through the experiments of the speaker identification, we show that the all the proposed have higher identification rates than the ML. In addition, the Hybrid and MWMR have higher identification rate about 2% and about 3% than WMR, respectively.

• The Journal of Korean Association of Computer Education
• /
• v.11 no.4
• /
• pp.47-58
• /
• 2008

The purpose of the study was to reveal the effects of visual organizer types and cognitive styles in electronic text understanding. 126 graduate students were divided into a field-dependent group and a field-independent group, and then assigned to two different types of web- based instruction programs which included visual organizers of 'reduction' type and 'abstraction' type. Regarding the comprehension of contents, there were no significant effects of visual organizer types and cognitive styles. However, it was revealed that there were significant interaction effects between visual organizer types and cognitive styles on the awareness of structure in electronic texts. That is to say, while Type 2 ('abstraction' type) was more effective to field-dependent learners, Type 1 ('reduction' type) was more effective to field-independent learners in awareness of structure in electronic texts.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.25-35
• /
• 1997

Most of speech analysis methods developed up to date are based on second order statistics, and one of the biggest drawback of these methods is that they show dramatical performance degradation in noisy environments. On the contrary, the methods using higher order statistics(HOS), which has the property of suppressing Gaussian noise, enable robust feature extraction in noisy environments. In this paper we propose a text-independent speaker identification system using higher order statistics and compare its performance with that using the conventional second-order-statistics-based method in both white and colored noise environments. The proposed speaker identification system is based on the vector quantization approach, and employs HOS-based voiced/unvoiced detector in order to extract feature parameters for voiced speech only, which has non-Gaussian distribution and is known to contain most of speaker-specific characteristics. Experimental results using 50 speaker's database show that higher-order-statistics-based method gives a better identificaiton performance than the conventional second-order-statistics-based method in noisy environments.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.2
• /
• pp.171-176
• /
• 2015

We present a speaker verification method by extracting i-vectors based on dominant state information of Hidden Markov Model (HMM) - Universal Background Model (UBM). Ergodic HMM is used for estimating UBM so that various characteristic of individual speaker can be effectively classified. Unlike Gaussian Mixture Model(GMM)-UBM based speaker verification system, the proposed system obtains i-vectors corresponding to each HMM state. Among them, the i-vector for feature is selected by extracting it from the specific state containing dominant state information. Relevant experiments are conducted for validating the proposed system performance using the National Institute of Standards and Technology (NIST) 2008 Speaker Recognition Evaluation (SRE) database. As a result, 12 % improvement is attained in terms of equal error rate.

• Hwankyungkyoyuk
• /
• v.6 no.1
• /
• pp.63-99
• /
• 1994

The international environmental activities and environmental education began in 1970's. Environmental education in Korea was emphasized since the Forth National Curriculum. 'The Environmental Education Curriculum' will be separated as one of the most important parts in the Sixth National Education Curriculum in Korea. The purpose of this study was development. of 'Environmental Science' of high school appropriate to Sixth National Education Curriculum. First step was to state goals of environmental education in detail based on analysis of goals about environmental education in our country and other countries. Second was to analyse seven environments-related texts of Korea, America and England. Third, to measure how much environmental education has achieved in Fifth National Curriculum of Korea. Fourth, to develop a new environmental text of high school level. Fifth, to verify the effect of developed environmental text. The environmental part of 'Science I'(unit V. Life and Environments) and high school environments-related reference text(Survival and Environments) in Korea, American knowledges. American 'Environments' was stressed in many skills but they didn't include various teaching strategies. On the other hand, American 'Science-Technology-Society(S-T-S)' and British 'Science and Technology in Society(SATIS)' were stressed in knowledges and skills, and they included many teaching strategies and student actions. American 'S-T-S' was the only one stressed in values and attitudes. And all seven texts were not interested in behaviors and participations. To measure the achievement of environmental education by questionnaire, 497 high school students in total were selected from five different schools. Actually, most students had a positive thinkings and attitudes in their hearts about environmental problems, about environmental problems, but many of them did not take actions to solve environmental problems and to protect environments. The higher the score students got in 'knowledges and informations', the higher the score in 'skill'. It implies that learning of skills is based on learning of knowledges and informations about environments. On the other hand, much knowledges and information about environments has not always ensured positive thinkings and attitudes or active behaviors and participations to solve environmental problem. In view that ultimate aim of environmental education is forming responsible environmental behaviors and the goals of values and behaviors are as important as knowledges and skills. A new environmental text of high school level was developed and it was based on analysis of seven texts and environmental education in Fifth Korean Curriculum. This text have seven units, 1. Habitates : What're the meanings?, 2. Nuclear Energy : Can't be Avoid?, 3. Acid Rain : What're the Messages?, 4. Ethanol : Is this Future Fuel?, 5. Wastes : A New War!, 6. What're the National and Gloval Environmental education and avoided from the array of knowledges. Therefore included various teaching strategies and independent actions of students. 'Open-ended value learning' and 'free behavior learning' in text were special learning parts for aquisition of values and formation of behaviors. To verify the effects. of new developed environmental text, the direct learning was carried out by 286 students in total. Post test scores of experimental groups per each units were significantly higher than those of control groups from five different schools were as follows. For validity of selecting contents for units, 74% of respondent replied positively. For classification and presentation of four goal-groups, 90% replied positively in validity and 82%, in utility. For validity of various teaching strategies, 88% and for the degree of including student-centered independent actions, 86% replied positively, For importances and expected effects of 'open=ended value learning' and 'free behavior learning', showed positive responses respectively, 88%, 92% Therefore this text is effective to achieve four goals of environmental education equally.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.640-645
• /
• 2021

The deep learning based end-to-end TTS system consists of Text2Mel module that generates spectrogram from text, and vocoder module that synthesizes speech signals from spectrogram. Recently, by applying deep learning technology to the TTS system the intelligibility and naturalness of the synthesized speech is as improved as human vocalization. However, it has the disadvantage that the inference speed for synthesizing speech is very slow compared to the conventional method. The inference speed can be improved by applying the non-autoregressive method which can generate speech samples in parallel independent of previously generated samples. In this paper, we introduce FastSpeech, FastSpeech 2, and FastPitch as Text2Mel technology, and Parallel WaveGAN, Multi-band MelGAN, and WaveGlow as vocoder technology applying non-autoregressive method. And we implement them to verify whether it can be processed in real time. Experimental results show that by the obtained RTF all the presented methods are sufficiently capable of real-time processing. And it can be seen that the size of the learned model is about tens to hundreds of megabytes except WaveGlow, and it can be applied to the embedded environment where the memory is limited.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.2
• /
• pp.48-52
• /
• 1999

In this paper, we describe a Voice Command Web Browser using a variable vocabulary word recognizer that can do Internet surfing with Korean speech recognition on the Web. The feature of this browser is that it can handle the links and menus of the web browser by speech. Therefore, we can use speech interface together with mouse for web browsing. To recognize the recognition candidates dynamically changing according to Web pages, we use the variable vocabulary word recognizer. The recognizer was trained using POW (Phonetically Optimized Words) 3,848 words. So that it can recognize new words which did not exist in training data. The preliminary test results showed that the performance of speaker-independent and vocabulary-independent recognition is 93.8% for 32 Korean words. The Voice Command Web Browser was developed on windows 95/NT using Netscape Navigator and reflected usability test results in order to offer easy interface to users unfamiliar with speech interface. In on-line experiment of speaker-independent and environment-independent situation, Voice Command Web Browser showed recognition accuracy of 90%.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.523-529
• /
• 2021

In this paper, we designed and developed an Emotional Speech Synthesis Markup Language (SSML) processor. Multi-speaker emotional speech synthesis technology that can express multiple voice colors and emotional expressions have been developed, and we designed Emotional SSML by extending SSML for multiple voice colors and emotional expressions. The Emotional SSML processor has a graphic user interface and consists of following four components. First, a multi-speaker emotional text editor that can easily mark specific voice colors and emotions on desired positions. Second, an Emotional SSML document generator that creates an Emotional SSML document automatically from the result of the multi-speaker emotional text editor. Third, an Emotional SSML parser that parses the Emotional SSML document. Last, a sequencer to control a multi-speaker and emotional Text-to-Speech (TTS) engine based on the result of the Emotional SSML parser. Based on SSML which is a programming language and platform independent open standard, the Emotional SSML processor can easily integrate with various speech synthesis engines and facilitates the development of multi-speaker emotional text-to-speech applications.