• 한국초등과학교육학회지:초등과학교육
• /
• 제38권3호
• /
• pp.331-344
• /
• 2019

This study aims to analyse science-gifted elementary students' perception of speech in general school class, school science class, and science-gifted class and the relationship between their voluntary speech and scientific creativity. For this, 39 fifth-graders in the Science-Gifted Education Center at Seoul Metropolitan Office of Education in Korea were asked about their frequency of voluntary speech on each class situation, the reasons for such behavior, and their general opinions about speech. Also, researchers collected the teachers' observation on students' speech in class. To get the scores for students' scientific creativity, four different subjects of tasks were presented. The students' scientific creativity scores were used for correlation analysis with their frequency of speech. The main findings from this study are as follows: First, science-gifted elementary students tended to be passive in science-gifted class compared to general school and school science class. Second, the main reason for the low frequency of students' speech in school classes is that they do not have many opportunities to make presentations. Third, a survey of students' general thoughts on speech showed that more students wanted to make a speech voluntarily in class than the opposite. Fourth, the four different scientific creativity tasks had little correlation. Fifth, the correlations between the frequency of voluntary speech and the scores of scientific creativity were mostly low, with significant results only for plant task. Sixth, the correlations between the frequency of voluntary speech and the two components that make up scientific creativity, originality and usefulness, were also mostly low, but significant results for both were found in plant task, with originality having a higher correlation than usefulness. Based on this results, this study discussed the meanings and implications of students' voluntary speech on elementary science education and creativity education.

• ETRI Journal
• /
• 제18권1호
• /
• pp.29-41
• /
• 1996

This paper describes a method to select a suitable feature for speech recognition using information theoretic measure. Conventional speech recognition systems heuristically choose a portion of frequency components, cepstrum, mel-cepstrum, energy, and their time differences of speech waveforms as their speech features. However, these systems never have good performance if the selected features are not suitable for speech recognition. Since the recognition rate is the only performance measure of speech recognition system, it is hard to judge how suitable the selected feature is. To solve this problem, it is essential to analyze the feature itself, and measure how good the feature itself is. Good speech features should contain all of the class-related information and as small amount of the class-irrelevant variation as possible. In this paper, we suggest a method to measure the class-related information and the amount of the class-irrelevant variation based on the Shannon's information theory. Using this method, we compare the mel-scaled FFT, cepstrum, mel-cepstrum, and wavelet features of the TIMIT speech data. The result shows that, among these features, the mel-scaled FFT is the best feature for speech recognition based on the proposed measure.

• 한국통신학회논문지
• /
• 제33권3C호
• /
• pp.234-239
• /
• 2008

For the efficient coding and transmission, the speech signal can be classified into three distinctive classes: voiced, unvoiced, and transition classes. At low bit rate coding below 4 kbit/s, conventional sinusoidal transform coders synthesize speech of high quality for the purely voiced and unvoiced classes, whereas not for the transition class. The transition class including plosive sound and abrupt voiced-onset has the lack of periodicity, thus it is often classified and synthesized as the unvoiced class. In this paper, the efficient algorithm for the transition class detection is proposed, which demonstrates superior detection performance not only for clean speech but for noisy speech. For the detected transition frame, phase information is transmitted instead of magnitude information for speech synthesis. From the listening test, it was shown that the proposed algorithm produces better speech quality than the conventional one.

• 대한음성학회지:말소리
• /
• 제60호
• /
• pp.145-164
• /
• 2006

This paper proposes class histogram equalization (CHEQ) to compensate noisy acoustic features for robust speech recognition. CHEQ aims to compensate for the acoustic mismatch between training and test speech recognition environments as well as to reduce the limitations of the conventional histogram equalization (HEQ). In contrast to HEQ, CHEQ adopts multiple class-specific distribution functions for training and test environments and equalizes the features by using their class-specific training and test distributions. According to the class-information extraction methods, CHEQ is further classified into two forms such as hard-CHEQ based on vector quantization and soft-CHEQ using the Gaussian mixture model. Experiments on the Aurora 2 database confirmed the effectiveness of CHEQ by producing a relative word error reduction of 61.17% over the baseline met-cepstral features and that of 19.62% over the conventional HEQ.

• ETRI Journal
• /
• 제28권4호
• /
• pp.502-505
• /
• 2006

A new class-based histogram equalization method is proposed for robust speech recognition. The proposed method aims at not only compensating the acoustic mismatch between training and test environments, but also at reducing the discrepancy between the phonetic distributions of training and test speech data. The algorithm utilizes multiple class-specific reference and test cumulative distribution functions, classifies the noisy test features into their corresponding classes, and equalizes the features by using their corresponding class-specific reference and test distributions. Experiments on the Aurora 2 database proved the effectiveness of the proposed method by reducing relative errors by 18.74%, 17.52%, and 23.45% over the conventional histogram equalization method and by 59.43%, 66.00%, and 50.50% over mel-cepstral-based features for test sets A, B, and C, respectively.

• 수산해양교육연구
• /
• 제28권3호
• /
• pp.808-817
• /
• 2016

This study aims at reviewing differences of awareness toward speech-language therapy according to background variables of child-care teachers, and establishing a basic data necessary for special education support programs afterwards based on child-care centers and its characteristics with the results. Researcher carried out a survey by objecting child-care teachers of Chungcheongbuk-do, Korea, and looked into existence of some differences through SPSS 20.0 for Window, independent sample t-Test, ANOVA, Scheffe post verification on background characteristics such as level of education, working career, license grade, whether or not to have objects of speech-language objects in the class. Research results are same as follows. First, significant differences in awareness of child-care teachers toward speech-language therapy appeared from license grade among characteristics like level of education, license grade, whether or not to have objects of speech-language therapy in the class. Second, significant differences were displayed from whether or not to have objects of speech-language therapy in the class among characteristics such as level of education, working career, license grade, and whether or not to have objects of speech-language therapy. When putting these results together, a conclusion could be made such like awareness of child-care teachers toward speech-language therapy and therapists is able to be different a little according to background variables of teachers.

• ETRI Journal
• /
• 제30권5호
• /
• pp.753-755
• /
• 2008

In this letter, we propose a new histogram equalization technique for feature compensation in speech recognition under noisy environments. The proposed approach combines a signal-to-noise-ratio-dependent feature reconstruction method and the class histogram equalization technique to effectively reduce the acoustic mismatch present in noisy speech features. Experimental results from the Aurora 2 task confirm the superiority of the proposed approach for acoustic feature compensation.

• 한국컴퓨터정보학회논문지
• /
• 제29권1호
• /
• pp.287-293
• /
• 2024

본 연구는 인공지능을 활용한 수업이 항공전문학교 학생의 인지적으로 미치는 영향을 검증하였다. 먼저 프레젠테이션을 활용한 수업에서 전통적인 멀티미디어 자료 기반의 수업과 Speech-to-text(STT)기반의 인공지능 자료로 구성된 수업을 개발하였다. A 항공 전문 교육기관의 학생 133명이 두 가지 유형의 수업에 참여하였다. 수업 전후에 학생들의 인지 부하와 Mind Wandering을 측정하였고, 성취도평가를 실시하였다. 검사의 분석 결과, 외재적 인지 부하는 감소하였고 콘텐츠 집중도가 높아졌으며 성취도가 향상됨을 확인하였다. 향후 기술을 지도하는 학교에서 인공지능 기반의 STT수업이 많이 활용되기를 기대한다.

• 비교문화연구
• /
• 제37권
• /
• pp.287-307
• /
• 2014

The purpose of this paper is to introduce a new and effective classroom speaking activity helping student's communication in real situation. It will be one of useful teaching techniques for teachers because it can be used with other various types of speaking activities together. The activity is designed by the researcher, and named as the Partner's Speech Reconstitution(PSR) in this paper. In chapter 2, Noticing and Output hypothesis which is the theoretic basis of the PSR will be described and the chapter 3 will explain activity methods and examples of the PSR, and then describe its merits and demerits. The researcher applied and practiced the PSR in the speaking class for international students in the K university for three semesters. This paper systematically introduces its organized activity. It helped learners elicit speaking performance of students who avoided talking in the speaking class, made the students concentrate in speaking activity, and helped the learners to talk sufficiently by inducing each student to reconstitute partner's speech production.

• 말소리와 음성과학
• /
• 제11권4호
• /
• pp.1-8
• /
• 2019

This study aims to investigate how prosodic prominence is perceived in relation to word class information (or parts-of-speech) by Korean learners of English compared with native English speakers in public speech. Two groups, Korean learners of English and native English speakers, were asked to judge words perceived as prominent simultaneously while listening to a speech. Parts-of-speech and three acoustic cues (i.e., max F0, mean phone duration, and mean intensity) were analyzed for each word in the speech. The results showed that content words tended to be higher in pitch and longer in duration than function words. Both groups of listeners rated prominence on content words more frequently than on function words. This tendency, however, was significantly greater for Korean learners of English than for native English speakers. Among the parts-of-speech of the content words, Korean learners of English were more likely than native English speakers to judge nouns and verbs as prominent. This study presents evidence that Korean learners of English consider most, if not all, content words as landing locations of prosodic prominence, in alignment with the previous study on the production of prominence.