• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.1
• /
• pp.11-22
• /
• 1994

For the conventional systme based on word, it is very difficult to enlarge the number of vocabulary. To cope with this problem, we must use more fundamental units of speech. For example, syllables and phonemes are such units, Korean speech consists of initial consonants, middle vowels and final consonants and has characteristic that we can obtain syllables from speech easily. In this paper, we show a speech recognition system with the advantage of the syllable characteristics peculiar to the Korean speech. The algorithm of recognition system is the Time Delay Neural Network. To recognize many recognition units, system consists of initial consonants, middle vowels, and final consonants recognition neural network. At first, our system recognizes initial consonants, middle vowels and final consonants. Then using this results, system recognizes isolated words. Through experiments, we got 85.12% recognition rate for 2735 data of initial consonants, 86.95% recognition rate for 3110 data of middle vowels, and 90.58% recognition rate for 1615 data of final consonants. And we got 71.2% recognition rate for 250 data of isolated words.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.107-110
• /
• 1994

In this paper, we describe the features of the fundamental frequency contour of Korean read speech, and propose a new stylization method to characterize the Fø pattern of segments. Our algorithm consists of three stylization processes : the segment level, the syllable level, and the sord level. For stylization of Fø contour in the segment level , we applied least square error minimization method to determine Fø values at initial, medial, and final position in a segment. In the syllable level, we determine the stylized Fø pattern of a syllable using the mean Fø value of each word and style information for each word, syllable and segment, we reconstruct Fø contour of sentences. The simulation results show that the error is less than 10% of the actual Fø contour for each sentence. In perception test, there is little difference between the synthesized speech with the original difference between the synthesized speech with the original Fø contour and the synthesized speech with the stylized Fø contour.

• Journal of Fisheries and Marine Sciences Education
• /
• v.29 no.3
• /
• pp.655-664
• /
• 2017

The purpose of this study was to verify the relationships among sport enjoyment, leisure satisfaction, and continuous participation intention in ski class. The study conducted a research survey through purposive sampling method. 280 questionnaires distributed and 271 were selected as final valid sample by removing 9 questionnaires that have insufficient answers. Hypothesis test on collected data was conducted by using SPSS 20.0 and AMOS 18.0 programs. The results were as followings. First, sport enjoyment factors a significant effect on psychological satisfaction, environmental satisfaction. Second, sport enjoyment factors had effect on re-participation intention, word of mouth intention. Third, leisure satisfaction had effect on re-participation intention, word of mouth intention. In addition, it had effect on continuos participation intention as the partial mediation of the leisure satisfaction.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1311-1314
• /
• 2003

In this paper, we propose a method to measure document similarity. First, we have exploited single-term method that extracts nouns by using a lexical analyzer as a preprocessing step to match one index to one noun. In spite of irrelevance between documents, possibility of increasing document similarity is high with this method. For this reason, a term-phrase method has been reported. This method constructs co-occurrence between two words as an index to measure document similarity. In this paper, we tried another method that combine these two methods to compensate the problems in these two methods. Six types of features are extracted from two input documents, and they are fed into a neural network to calculate the final value of document similarity. Reliability of our method has been proved by an experiment of document retrieval.

• MALSORI
• /
• no.56
• /
• pp.207-223
• /
• 2005

The goal of language model adaptation is to improve the background language model with a relatively small adaptation corpus. This study presents a language model adaptation technique where additional text data for the adaptation do not exist. We propose the information retrieval (IR) technique with N-gram language modeling to collect the adaptation corpus from baseline text data. We also propose to use a dynamic language model interpolation coefficient to combine the background language model and the adapted language model. The interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech data reserved for held-out validation data. This allows the final adapted model to improve the performance of the background model consistently The proposed approach reduces the word error rate by $13.6\%$ relative to baseline 4-gram for two-hour broadcast news speech recognition.

• Korean Journal of English Language and Linguistics
• /
• v.2 no.1
• /
• pp.23-30
• /
• 2002

Phonologically, the difference between the English stops /b, d, g/ and /p, t, k/ is carried by the presence or the absence of the vocal fold vibration throughout their oral closure phase. If phonology has its foundation in phonetics, there must be phonetic evidence for the voiced-voiceless distinction. This study is aimed to determine whether or not the voiced-voiceless distinction is acceptable or proper in English. The determination was based mainly on findings in the existing literature and in informal experiments. In conclusion, there is no phonetic evidence for the voiced-voiceless distinction both in production and perception. The [voice] appears to be one of potential phonetic correlates of the phonologically voiced stop. It is improper to use the [voice] as independent phonological marker, regardless of position (word-initial, intervocalic, word-final). A feature other than the voiced-voiceless feature must distinguish /b, d, g/ from /p, t, k/.

• Speech Sciences
• /
• v.13 no.2
• /
• pp.107-120
• /
• 2006

The main purpose of this study is to investigate whether Korean learners can use the vowel duration cue to distinguish voicing contrasts in word-final consonants in English. Given that the Korean group's performance on the auditory task was much better than their performance on the identification task or on the production task, we conclude that the AX discrimination task makes contact with a different layer of perception. In particular, the AX discrimination task can be done at the auditory or phonetic level, where differences in vowel length are still encoded in the representation. In contrast, the identification and production tasks are probing the mental representation of vowel length and voicing. It was also founded that Korean speakers stored neither vowel length nor voicing in memorized representations and did not internalize the lengthening of the preceding vowel as a rule to differentiate the voicing contrasts of final consonants, even though they were able to detect the acoustic differences in vowel duration provided that they were tested in an appropriate task.

• Speech Sciences
• /
• v.2
• /
• pp.135-147
• /
• 1997

This thesis describes pronunciation differences of vowel lengths between Koreans and Americans speaking English words and sentences. This study also analizes the reasons for these differences with the help of acoustic instruments. Sixteen sentences and eight words were selected as the experimental material. The informants for this study were 9 males; 3 Americans and 6 Koreans, who were asked to pronounce the test words and sentences five times. In this study, the acoustical analysis to measure duration was done through computer digital techniques. According to the results of the experiment, duration of 8 English vowels pronounced between Koreans and Americans shows very different features. When Koreans pronounce English vowels, the duration of the stressed vowel in the sentence-final position is much shorter than in other positions, such as in the sentence-initial and in word position. On the contrary, when Americans pronounce English vowels, the duration of the stressed vowel in the sentence-final position is much longer than in other positions. If the correlation between length and stress were to be studied in a more detailed manner, it would give fundamental help to the study of relation between stress and length.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.89-92
• /
• 1998

영어의 선행모음의 길이 특성이 어말 자음의 유.무성 인지에 어떤 영향을 미치는지에 관한 선행 연구의 후행연구로서 후행하는 폐쇄음의 자음적 특성은 어떠한 실마리로 적용하는지 한국어 화자들을 대상으로 한 인지실험을 통해 알아보았다. 실험결과, 한국어 모국어 화자들에게 어말 폐쇄음의 자음적 특성은 자음의 유.무성 인지에 중요한 실마리로 작용하지 못하고 있다는 사실을 알 수 있었다.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.285-287
• /
• 2007

The primary goal of this study is to find out how the effect of speaking rate has some influence on the production and perception across languages. Through both experiments of production and perception, an English native speaker changes both production and perception simultaneously. Especially the production of the temporal features changes relatively fast. On the contrary, Chinese and Korean speakers changes their production rather than perception by following the speaking rate.