• 한국음향학회지
• /
• 제10권4호
• /
• pp.5-11
• /
• 1991

본 연구에서는 음성신호의 음소 단위 구분화 방법을 제안한다. 제안된 구분화 시스템은 화자 독립적이고, 음성신호에 대한 사전 정보 없이도 음소 단위로 구분화를 수행할 수 있는 특징을 갖는다. 구분화 처리는 입력 음성신호를 먼저 순수 유성을 구간과 순수 유성음이 아닌 구간으로 분리 시킨 후, 각각의 구간에 대해 세분화된 음소 단위로 분리시키는 2단계 구분화 알고리즘을 적용하였고, 이때 사용된 파라미터는 유성을 검출 파라미터, 영차 LPC 캡스트럼 계수의 시간변호 파라미터, ZCR 파라미터이다. 본 연구에서 제안한 구분화 알고리즘의 유용성을 입증하기 위해 사용한 대상어는 고립단어와 연속음성으로 구성된 어휘로서 전체 어휘중에 포함된 507개 음소에 대한 구분화율은 91.7% 이다.

• 음성과학
• /
• 제13권4호
• /
• pp.69-87
• /
• 2006

This study aims to describe the vowel system of present-day American English and to discuss some of its phonetic variations due to regional differences. Fifteen speakers of American English from various regions of the United States produced the monophthongs of English. The vowel duration and the frequencies of the first and the second formant were measured. The results indicate that the distinction between the vowels [c] and [a] has been merged in most parts of the U.S. except in some speakers from eastern and southeastern parts of the U.S., resulting in the general loss of phonemic distinction between the vowels. The phonemic merger of the two vowels can be interpreted as the result of the relatively small functional load of the [c]-[a] contrast, and the smaller back vowel space in comparison to the front vowel space. The study also shows that the F2 frequencies of the high back vowel [u] were extremely high in most of the speakers from the eastern region of the U.S., resulting in the overall reduction of their acoustic space for high vowels. From the viewpoint of the Adaptive Dispersion Theory proposed by Liljencrants & Lindblom (1972) and Lindblom (1986), the high back vowel [u] appeared to have been fronted in order to satisfy the economy of articulatory gesture to some extent without blurring any contrast between [i] and [u] in the high vowel region.

• 대한음성학회지:말소리
• /
• 제55권
• /
• pp.103-118
• /
• 2005

In this paper, we describe a morpheme-based pronunciation lexicon useful for Korean LVCSR. The phonemic-context-dependent multiple pronunciation lexicon improves the recognition accuracy when cross-morpheme pronunciation variations are distinguished from within-morpheme pronunciation variations. Since adding all possible pronunciation variants to the lexicon increases the lexicon size and confusability between lexical entries, we have developed a lexicon pruning scheme for optimal selection of pronunciation variants to improve the performance of Korean LVCSR. By building a proposed pronunciation lexicon, an absolute reduction of $0.56\%$ in WER from the baseline performance of $27.39\%$ WER is achieved by cross-morpheme pronunciation variations model with a phonemic-context-dependent multiple pronunciation lexicon. On the best performance, an additional reduction of the lexicon size by $5.36\%$ is achieved from the same lexical entries.

• 한국음향학회지
• /
• 제20권2호
• /
• pp.35-43
• /
• 2001

음성 인식이나 음성 합성시 필요한 발음열을 수작업으로 작성할 경우 작성자의 음운변화 현상에 대한 전문적 언어지식을 비롯하여 많은 시간과 노력이 요구되며 일관성을 유지하기도 쉽지 않다. 또한 한국어의 음운 변화 현상은 단일 형태소의 내부와 복합어에서 결합된 형태소의 경계점, 여러 형태소가 결합해서 한 어절을 이룰 경우 그 어절 내부의 형태소의 경계점, 여러 어절이 한 어절을 이룰 때 구성 어절의 경계점에서 서로 다른 적용 양상을 보인다. 본 논문에서는 이러한 문제를 해결하기 위해서 형태음운론적 분석에 기반하여 문자열을 자동으로 발음열로 변환하는 발음 생성 시스템을 제안하였다. 이 시스템은 한국어에서 빈번하게 발생하는 음운변화 현상의 분석을 통해 정의된 음소 변동 규칙과 변이음 규칙을 다단계로 적용하여 가능한 모든 발음열을 생성한다. 각 음운변화 규칙을 포함하는 대표적인 언절 리스트를 이용하여 구성된 시스템의 안정성을 검증하였고, 발음사전 구성과 학습용 발음열의 유용성을 인식 실험을 통해 평가하였다. 그 결과 표제어 사이의 음운변화 현상을 반영한 발음사전의 경우 5-6％ 정도 나은 단어 인식률을 얻었으며, 생성된 발음열을 학습에 사용한 경우에서도 향상된 결과를 얻을 수 있었다.

• 한국음향학회지
• /
• 제21권4호
• /
• pp.401-406
• /
• 2002

한국어 숫자는 모두 단음절로 이루어져 있으며, 연속적으로 발음될 때 인접 숫자들의 상호조음현상에 의해 각 숫자의 고유 발음이 변화하고, 또한 그 숫자들의 경계도 모호해지는 문제점이 있다. 이러한 문제점들과 더불어 배경잡음이나 채널에 의한 왜곡에 따른 문제점들로 인해 한국어 연결숫자의 인식 성능은 만족스럽지 못한 것이 현실이다. 본 논문에서는 연결숫자의 인식성능 향상을 위해서 한국어 숫자들의 음운변화를 고려하여 유사음소 (phonelike units: PLUs)군을 정의하고, 사용자의 여러 가지 발성형태에 따른 다양한 음운 현상의 변화를 흡수할 수 있도록 인식 시스템을 구성하는 방식을 검토하였다. 전화망 4연숫자를 이용한 화자독립 인식 실험을 수행한 결과 제안된 방법의 숫자열 인식률은 상태당 믹스쳐 (mixture) 개수가 1인 경우 83.2%로, 기준 시스템 (baseline)에 대한 오류감소률이 7.2%였고 가장 높은 성능을 나타낸 믹스쳐 개수가 11인 경우 숫자열 인식률은 91.8% 오류감소율은 4.7%였다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.75-78
• /
• 2003

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon for Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished pronunciation variation rules according to the locations such as within a morpheme, across a morpheme boundary in a compound noun, across a morpheme boundary in an eojeol, and across an eojeol boundary. In 33K-morpheme Korean CSR experiment, an absolute improvement of 1.16％ in WER from the baseline performance of 23.17％ WER is achieved by modeling cross-morpheme pronunciation variations with a context-dependent multiple pronunciation lexicon.

• 대한음성학회지:말소리
• /
• 제49호
• /
• pp.107-121
• /
• 2004

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon to improve the performance of a Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished phonological rules that can be applied to phonemes in within-morpheme and cross-morpheme. The results of 33K-morpheme Korean CSR experiments show that an absolute reduction of 1.45% in WER from the baseline performance of 18.42% WER was achieved by modeling proposed pronunciation variations with a possible multiple context-dependent pronunciation lexicon.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2000년도 7월 학술대회지
• /
• pp.166-177
• /
• 2000

The purpose of this study was to create letters for of nonliterary Pulang tribe in Thailand those who immigrant from China. illiterate Pulang tribe hand down their tradition by primary oral culture therefore their tradition can't initiate and keep, moreover, it may disappear throughout history. So it is expected to crusade against unlettered people. The scheme of research adopted in this study was a minority race who habitate at the northern Machan, Chiangrai in Thailand. It is not only analysis of language but also the eradication of literacy and the research based on linguistic, ethnolinguistic, and primary oral culture. Five Pulang people who live in that area were chosen for creating letters. By using the I. P. A., after each word was listen to their pronunciation one by one it was described and repeated this process several times; the material words and humanbody were pointed in front of them while other words were described by gesture. For final description, number of people were in the lineup for listening the sound of words and phrases to sentences. In the first stage, it was an analysis segmental of Pulang: vocoid, contoid and diphthong were described with each sample syllables and words. The suprasegmental were studied with intonation and juncture of the words in the second stage. Two words were compared and different meanings within their intonation and juncture were shown. At the end of this part, each case of phonemic or morphophonemics representation described the juncture in the words. In the third stage, minimal pairs were analyzed with vowels and consonants and described in free variation based on words. In the last stage, syllable structure in open syllable and closed syllable was studied and then each syllable of its structure was analyzed with samples. There were thirty-two phonemes in apong Pulang as follows: seven vocoids; a, i, e, o, u, ${\ae}$, and $\wedge$, one diphthong; wu, 24 contoids; b, c, d, f, g, h, j, k, k, 1, m, n, ${\eta}, {\;}p^{h}$, p, p, r, s, s, sh, t, t, w, and y. Their pronunciations of p, s, d, $p^{h}$, j, and t are frequently used in speech and are unique in triphthong. Moreover, most of the words used initial and final consonant cluster.

• 말소리와 음성과학
• /
• 제8권3호
• /
• pp.11-20
• /
• 2016

It is well known that vowels are shorter before voiceless consonants than voiced ones in English, as in many other languages. Research has shown that the ratio of vowel durations in voiced and voiceless contexts in English is in the range of 0.6~0.8. However, little work has been done as to whether the ratio of vowel durations varies depending on English variety. In the production experiment in this paper, seven speakers from three varieties of English, New Zealand, British, and American English, read 30 pairs of (C)VC monosyllabic words which differ in coda voicing (e.g. beat-bead). Vowel height, phonemic vowel length, and consonant manner were varied as well. As expected, vowel-shortening effects were found in all varieties: vowels were shorter before voiceless than before voiced codas. Overall vowel duration was the longest in American English and the shortest in New Zealand (NZ) English. In particular, vowel duration before voiceless codas is the shortest in New Zealand English, indicating the most radical degree of shortening in this variety. As a result, the ratio of vowel durations in varying voicing contexts is the lowest in NZ English, while American and British English do not show a significant difference each other. In addition, consonant closure duration was examined. Whereas NZ speakers show the shortest vowel duration before a voiceless coda, their voiceless consonants have the longest closure duration, which suggest an inverse relationship between vowel duration and closure duration.

• 말소리와 음성과학
• /
• 제11권4호
• /
• pp.63-70
• /
• 2019

This study investigated individual variability of L2 learners' categorical judgments of L2 stops by exploring English learners' perceptual processing of two acoustic cues (voice onset time [VOT] and f0) and working memory capacity as sources of variation. As prior research has reported that English speakers' greater use of the redundant cue f0 was responsible for gradient processing of native stops, we examined whether the same processing characteristics would be observed in L2 learners' perception of Korean stops (/t/-/t^h/). 22 English learners of L2 Korean with a range of L2 proficiency participated in a visual analogue scaling task and demonstrated variable manners of judging the L2 Korean stops: Some were more gradient than others in performing the task. Correlation analysis revealed that L2 learners' categorical responses were modestly related to individuals' utilizations of a primary cue for the stop contrast (VOT for L1 English stops and f0 for L2 Korean stops), and were also related to better working memory capacity. Together, the current experimental evidence demonstrates adult L2 learners' top-down processing of stop consonants where linguistic and cognitive resources are devoted to a process of determining abstract phonemic identity.