• 전자공학회논문지B
• /
• 제32B권1호
• /
• pp.147-153
• /
• 1995

In this paper, we propose the position- and size-independent handwritten on-line Korean character recognition system using multilayer neural networks which are trained with error back-propagation learning algorithm and the features of Hanguel consonants and vowels. Starting point, end point, and three vectors from starting point to end point of each stroke of characters inputted from mouse or tablet are applied as inputs of neural networks. If double consonants and vowels are separated by single consonants and vowels, all consonants and vowels have at most four strokes. Therefore, four neural networks learn the consonants and the vowels having each number of strokes. Also, we propose the algorithm of separating the consonants and vowels and constructing a character.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2000년도 7월 학술대회지
• /
• pp.189-198
• /
• 2000

/$t{\partial}n$/, /$d{\partial}n$/, /$t{\partial}l$/ and /d{\partial}l$/, on the one hand, are the typical phonemes of syllabic consonants. On the other hand, /${\int}{\partial}n$/ most plausibly gives rise to the syllabic consonants. /$t{\partial}r$/ and /$d{\partial}r/ can he syllabic. However, because lip-rounded consonants strengthen the character of consonantal phonemes, they are not so appropriate. Apart from phonemes, some familiar words also could be almost always syllabic. From the historical perspective, we can say that the position of syllabic consonants is typically the second syllables of two-syllabic words and 1.hat the underlying schwa does not always exist. In terms of the syllable structure, the syllables which include syllabic consonants are totally different from both stressed syllables and the other unstressed syllables.

• 말소리와 음성과학
• /
• 제1권2호
• /
• pp.95-103
• /
• 2009

We investigated the perceptual structure of Korean consonants by analyzing the confusion among consonants in various vowel contexts. The 36 CV syllable types combined by 18 consonants and 2 vowels (/i/ and /u/) were presented with masking noises or in degraded intensity. The confusion data were analyzed by the INDSCAL (Individual Difference Scaling), ADCLUS (Additive Clustering) and the probability of the transmitted information. The results were compared with those of a previous study with /a/ vowel context (Bae and Kim, 2002). The overall results showed that the laryngeal features-aspiration, lax and tense-are the most salient features in the perception of Korean consonant regardless of vowel contexts, but the perceptual saliency of place features varies across vowel conditions. In high vowel (front and back vowel) contexts, sibilant consonants were perceptually salient compared to in low vowel contexts. In back vowel contexts, grave (labial and velar) consonants were perceptually salient. These findings imply that place features and vowel features strongly interact in speech perception as well as in speech production. All statistical measures from our confusion data ensured that the perceptual structure of Korean consonants correspond to the hierarchical structure suggested in the feature geometry (Clements, 1991). We discuss the link between speech perception and production as the basis of phonology.

• Acta Via Serica
• /
• 제3권1호
• /
• pp.85-102
• /
• 2018

This study aims to contrast phonological characteristics of Korean and Turkish in terms of language universality. Considering consonants, both languages have the same number of consonants (21), which is the most typologically plausible structure of consonants. Thus, it can be said that they display high universality in the number of consonants. However, Turkish shows higher universality in regards to their substance, i.e., it differs from Korean when it comes to the structure of plosives and affricates. Turkish has two contrastive consonants, i.e., voiced and voiceless. However, the Korean plosives and affricates consist of neutral, tense and aspirate voiceless. In the case of vowels, both Korean with 10 vowels and Turkish with 8 vowels show lower universality. Yet, all of those vowels belong to the list of the most plausible vowels which makes their universality higher in substance. In respect of the syllable structure, Korean with its (C)V(C) type shows a moderately complex structure while Turkish with its (C)V(C)(C) type has a complex structure. The coda may consist of two consonants in Turkish while only one consonant is possible in Korean. However, onset is composed of one consonant in both languages. The contrastive study of similarities and differences between Korean and Turkish in terms of phonological characteristics will help not only understand the two languages but also provide useful information to increase the efficacy of Korean language education for Turkish learners of Korean, whose number is rapidly increasing.

• 음성과학
• /
• 제1권
• /
• pp.83-101
• /
• 1997

This paper aims at exploring a putative positional neutralization produced at the phonetics/phonology interface. It was designed to determine whether Korean intervocalic laryngeal consonants are phonetically distant from geminates, plain consonants, or laryngeal consonants in consonant clusters. It was found that the contrast between laryngeal singletons and geminates was neutralized intervocalically, and that both of these were patterned with heteroganic consonant sequences rather than with plain singletons.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1991년도 학술발표회 논문집
• /
• pp.73-77
• /
• 1991

As the basic analysis to solve the stop consonants in phoneme based speech recognition using Back Propagation learning algorithm, changes in hidden units, training set and iteration. Also we propose an efficient processing method of separation between consonants and vowels.

• 말소리와 음성과학
• /
• 제3권4호
• /
• pp.23-31
• /
• 2011

This paper examines the production patterns of the acquisition of coda consonants in monosyllabic words in English-speaking children with cochlear implants. The data come from the transcribed speech of children with cochlear implants. This study poses three questions. First, do children with cochlear implants acquire onset consonants earlier than codas? Second, do children's productions have a bimoraic-sized constraint that maintains binary feet? Third, what patterns emerge from production of coda consonants? The results revealed that children with cochlear implants acquire onset consonants earlier than codas. With regard to the bimoraic-sized constraints, the productions of vowel type (i.e., monomoraic and bimoraic) were more accurate for monomoraic vowels than bimoraic ones for some children with cochlear implants, although accuracy in vowel productions showed high proportion regardless of vowel types. The variations of coda production exhibited individual differences. Some children produced less sonorant consonants with high frequency and others produced more sonorant ones. The results of this study were similar to those pertaining to children with normal hearing. In the process of coda consonant acquisition, the error patterns of prosody-sensitive production may be regarded as articulatory challenges to produce higher-level prosodic structures.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2007년도 한국음성과학회 공동학술대회 발표논문집
• /
• pp.230-233
• /
• 2007

In the literature on the tense consonants in Korean, it has been proposed that this consonant is underlyingly represented by a single consonant (the singleton hypothesis) and that it is represented by a sequence of two lenis consonants (the geminate hypothesis). One piece of the empirical evidence supporting the geminate hypothesis is that the closure duration of tense consonants in intervocalic position is more than twice as long in comparison with their lenis counterparts. In this paper, we report on the closure duration of three types of plosives in various phonotactically permitted contexts in Korean. The results of the measurement show that the duration of the tense consonants in post-sonorant contexts is reduced by a third in comparison with that of the intervocalic ones. These temporal differences suggest that the measurement of closure durations in intervocalic position alone is not sufficient to sustain the geminate hypothesis.

• 음성과학
• /
• 제9권4호
• /
• pp.175-185
• /
• 2002

The purpose of this study was to investigate the acoustic durations of Korean vowels followed by either voiced or voiceless consonants. Six healthy adult speakers (2 females and 4 males) recorded nonsense syllables in which voiced (/b, d, g/) or voiceless (/p', t', k', $p^{h},t^{h},k^{h}$) consonants follow three different vowels (/i, a, u/) embedded in a carrier phrase. Results showed that vowels preceding voiced consonants (e.g., haba) were significantly longer in duration than those preceding voiceless consonants (e.g., hiP' a or $hip^{h}a$). Also vowels were longer in duration when occurring before velar-stops than before bilabial-stop and dental-stops. Finally, the duration of the low vowel (/a/) was substantially longer than that of the high vowels (/i, u/). These findings may be applicable to speech synthesis or therapy.

• 말소리와 음성과학
• /
• 제4권3호
• /
• pp.75-83
• /
• 2012

The aims of this study were three. First, to examine the degree of deviation from dictionary prescribed symbols and actual speech made by American English speakers. Second, to measure the frequency of vowel and consonant production of American English speakers. And third, to investigate gender differences in the segmental sounds in a speech corpus. The Buckeye Speech Corpus was recorded by forty American male and female subjects for one hour per subject. The vowels and consonants in both the phonemic and phonetic transcriptions were extracted from the original files of the corpus and their frequencies were obtained using codes of a free software R. Results were as follows: Firstly, the American English speakers produced a reduced number of vowels and consonants in daily conversation. The reduction rate from the dictionary transcriptions to the actual transcriptions was around 38.2%. Secondly, the American English speakers used more front high and back low vowels while three-fourths of the consonants accounted for stops, fricatives, and nasals. This indicates that the segmental inventory has nonlinear frequency distribution in the speech corpus. Thirdly, the two gender groups produced vowels and consonants similarly even though there were a few noticeable differences in their speech. From these results we propose that English teachers consider pronunciation education reflecting the actual speech sounds and that linguists find a way to establish unmarked segmentals from speech corpora.