• Korean Journal of Child Studies
• /
• v.28 no.4
• /
• pp.73-95
• /
• 2007

Causal relationships of kindergarteners' phonological awareness and processing to their ability to read words was investigated with the participation of 289 4- to 6-year-old children attending three kindergartens in Busan. Results showed gradual growth in reading ability with age. Children performed best in reading words and poorest in reading low frequency letters. They showed continuous development in skills of syllable deletion, phoneme substitution, phoneme insertion, phonological memory and naming. Discontinuous development was found in counting syllables. Longer syllables were difficult to count, and middle syllables of 3 syllable words were hard to delete. Children had poor perception of final consonants of Consonant-Vowel-Consonant syllables. Children's phonological awareness and processing were latent variables strongly related to ability to read words written in Hangul.

• MALSORI
• /
• no.63
• /
• pp.113-124
• /
• 2007

In this paper, we propose a use of confidence vector as an intermediate input feature for multi-stage based speech recognition architecture to improve recognition accuracy. A multi-stage speech recognition structure is introduced as a method to reduce the computational complexity of the decoding procedure and then accomplish faster speech recognition. Conventional multi-stage speech recognition is usually composed of three stages, acoustic search, lexical search, and acoustic re-scoring. In this paper, we focus on improving the accuracy of the lexical decoding by introducing a confidence vector as an input feature instead of phoneme which was used typically. We take experimental results on 220K Korean Point-of-Interest (POI) domain and the experimental results show that the proposed method contributes on improving accuracy.

• Speech Sciences
• /
• v.13 no.3
• /
• pp.97-105
• /
• 2006

The objective of this study was to analyze the acoustic patterns of Japanese /t/ produced by 40 Korean speakers in order to find an effective method of teaching it to Koreans. The experimental data consisted of 400 /t/ phonemes in word initial or non-initial positions of 10 words. Informants were in their twenties and raised in Daejeon and the surrounding area. Results showed that there were distinctive trends in duration and intensity of the major and non-major groups productions. Both groups pronounced the phoneme longer than the native speakers with more open mouths but with less loudness. The formant analysis showed that F1 values of the Japanese /t/ pronounced by Japanese major group were lower than those of the non-major. Its F2 values by the major group were higher than those of the non-major, which would suggest that the Koreans produced the tongue blade in more frontal position than the native speakers.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.18-21
• /
• 2003

In general it has been considered to be the difficult problem that we divide continuous speech into short interval with having identical phoneme quality. In this paper we used Gaussian Mixture Model (GMM) related to probability density to divide speech into phonemes, an initial, medial, and final sound. From them we peformed continuous speech recognition. Decision boundary of phonemes is determined by algorithm with maximum frequency in a short interval. Recognition process is performed by Continuous Hidden Markov Model(CHMM), and we compared it with another phoneme divided by eye-measurement. For the experiments result we confirmed that the method we presented is relatively superior in auto-segmentation in korean speech.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.1046-1051
• /
• 1994

It is known that SOFM has the property of effectively creating topographically the organized map of various features on input signals, SOFM can effectively be applied to the recognition of Korean phonemes. However, is isn't guaranteed that the network is sufficiently learned in SOFM algorithm. In order to solve this problem, we propose the learning algorithm combined with the conventional K-means clustering algorithm in fine-tuning stage. To evaluate the proposed algorithm, we performed speaker dependent recognition experiment using six phoneme classes. Comparing the performances of the Kohonen's algorithm with a proposed algorithm, we prove that the proposed algorithm is better than the conventional SOFM algorithm.

• Phonetics and Speech Sciences
• /
• v.10 no.2
• /
• pp.51-60
• /
• 2018

This study aims to compare the word decoding skills, phonological awareness (PA), rapid automatized naming (RAN) skills, and letter knowledge of first graders with developmental dyslexia (DD) and those who were typically developing (TD). Eighteen children with DD and eighteen TD children, matched by nonverbal intelligence and discourse ability, participated in the study. Word decoding of Korean language-based reading assessment(Pae et al., 2015) was conducted. Phoneme-grapheme correspondent words were analyzed according to whether the word has meaning, whether the syllable has a final consonant, and the position of the grapheme in the syllable. Letter knowledge asked about the names and sounds of 12 consonants and 6 vowels. The children's PA of word, syllable, body-coda, and phoneme blending was tested. Object and letter RAN was measured in seconds. The decoding difficulty of non-words was more noticeable in the DD group than in the TD one. The TD children read the syllable initial and syllable final position with 99% correctness. Children with DD read with 80% and 82% correctness, respectively. In addition, the DD group had more difficulty in decoding words with two patchims when compared with the TD one. The DD group read only 57% of words with two patchims correctly, while the TD one read 91% correctly. There were significant differences in body-coda PA, phoneme level PA, letter RAN, object RAN, and letter-sound knowledge between the two groups. This study confirms the existence of Korean developmental dyslexics, and the urgent need for the inclusion of a Korean-specific phonics approach in the education system.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.765-774
• /
• 2002

The purpose of this paper is a design and implementation for korean character and pen-gesture recognition system in multimedia terminal, PDA and etc, which demand both a fast process and a high recognition rate. To recognize writing-types which are written by various users, the korean character recognition system uses a database which is based on the characteristic information of korean and the stroke information Which composes a phoneme, etc. In addition. it has a fast speed by the phoneme segmentation which uses the successive process or the backtracking process. The pen-gesture recognition system is performed by a matching process between the classification features extracted from an input pen-gesture and the classification features of 15 pen-gestures types defined in the gesture model. The classification feature is using the insensitive stroke information. i.e., the positional relation between two strokes. the crossing number, the direction transition, the direction vector, the number of direction code. and the distance ratio between starting and ending point in each stroke. In the experiment, we acquired a high recognition rate and a fart speed.

• Journal of KIISE:Software and Applications
• /
• v.37 no.12
• /
• pp.946-950
• /
• 2010

Many sentiment categorization systems based on machine learning methods use morphological analyzers in order to extract linguistic features from sentences. However, the morphological analyzers do not generally perform well in a customer review domain because online customer reviews include many spacing errors and spelling errors. These low performances of the underlying systems lead to performance decreases of the sentiment categorization systems. To resolve this problem, we propose a feature extraction method based on simple longest matching of Eojeol (a Korean spacing unit) and phoneme patterns. The two kinds of patterns are automatically constructed from a large amount of POS (part-of-speech) tagged corpus. Eojeol patterns consist of Eojeols including content words such as nouns and verbs. Phoneme patterns consist of leading consonant and vowel pairs of predicate words such as verbs and adjectives because spelling errors seldom occur in leading consonants and vowels. To evaluate the proposed method, we implemented a sentiment categorization system using a SVM (Support Vector Machine) as a machine learner. In the experiment with Korean customer reviews, the sentiment categorization system using the proposed method outperformed that using a morphological analyzer as a feature extractor.

• MALSORI
• /
• no.37
• /
• pp.23-48
• /
• 1999

To improve the performance of automatic labelling system, the context-dependent demiphone unit was proposed. A phone is divided into two parts: a left demiphone that accounts for the left side coarticulation and a right demiphone that copes with the right side context. Demiphone unit provides a better training of the transition between phones. In this paper, If the length of the phone is less than 120 msec, it is split into two demiphones. If the length of the phone is greater than 120 msec, it is divided into three parts. In order to evaluate the performance of the system, we use 452 phonetically balanced words(PBW) database for training and testing phoneme models. According to the experiment, the system using proposed demiphone unit compared with that using old demiphone unit gains 3.83% improved result(71.63%) within 10ms of the duo boundary, and 2.20% improved result(86.41%) within 20ms of the true boundary.

• MALSORI
• /
• no.43
• /
• pp.73-88
• /
• 2002

In this paper, for natural facial synthesis, lip-synch algorithm based on key-frame method using RBF(radial bases function) is presented. For lips synthesizing, we make viseme range parameters from phoneme and its duration information that come out from the text-to-speech(TTS) system. And we extract viseme information from Av DB that coincides in each phoneme. We apply dominance function to reflect coarticulation phenomenon, and apply bilinear interpolation to reduce calculation time. At the next time lip-synch is performed by playing the synthesized images obtained by interpolation between each phonemes and the speech sound of TTS.