• 말소리와 음성과학
• /
• 제1권3호
• /
• pp.103-108
• /
• 2009

This paper proposes a method for building a transliteration dictionary, which is based on pronouncing information extracted from two kinds of existing dictionaries. Also, it proposes a method for transforming the pronouncing information into Korean translitered words. To express the pronouncing information, we define Phoman code system. In order to avoid phonetic estimation process of English words which is the most important problem, the proposed method uses the pronouncing information extracted from the existing dictionaries. Therefore, unlike previous approaches, the proposed method does not need any incomplete phonetic estimation process so that it can produce accurate transliteration results. The proposed method has been fully implemented.

• 말소리와 음성과학
• /
• 제8권2호
• /
• pp.11-16
• /
• 2016

This study explores the phoneme distribution and syllable structure of entry words in the CMU English Pronouncing Dictionary to provide phoneticians and linguists with fundamental phonetic data on English word components. Entry words in the dictionary file were syllabified using an R script and examined to obtain the following results: First, English words preferred consonants to vowels in their word components. In addition, monophthongs occurred much more frequently than diphthongs. When all consonants were categorized by manner and place, the distribution indicated the frequency order of stops, fricatives, and nasals according to manner and that of alveolars, bilabials and velars according to place. These results were comparable to the results obtained from the Buckeye Corpus (Yang, 2012). Second, from the analysis of syllable structure, two-syllable words were most favored, followed by three- and one-syllable words. Of the words in the dictionary, 92.7% consisted of one, two or three syllables. This result may be related to human memory or decoding time. Third, the English words tended to exhibit discord between onset and coda consonants and between adjacent vowels. Dissimilarity between the last onset and the first coda was found in 93.3% of the syllables, while 91.6% of the adjacent vowels were different. From the results above, the author concludes that an analysis of the phonetic symbols in a dictionary may lead to a deeper understanding of English word structures and components.

• 전자공학회논문지C
• /
• 제36C권3호
• /
• pp.47-56
• /
• 1999

한국어를 연속적으로 발음할 때 여러 가지 음은변동이 일어난다. 이러한 음운변동은 한국어 연속 음성 인식을 어렵게 하는 주요 요인 중의 한가지이다. 본 논문에서는 음운변동이 반영된 음성 인식 문자열을 규칙에 의하여 text 기반 문자열로 다시 복원시키는 rule-based 시스템을 제안한다. 그리고 복원 결과들은 형태소 분석되어 올바른 문자열만 생성된다. 복원은 4가지 rule 즉, 음절 경계 종성 초성 복원 rule, 모음처리 복원 rule,끝음절 종성 복원 rule, 한 음절 처리 rule에 의거하여 이루어진다. 규칙 적용 과정 중에 효과적인 복원을 위해 x-clustering정보를 정의하여 사용하고, 형태소 분석기에 입력될 복원 후보수를 제안하기 위해 postfix음절 빈도정보를 구하여 사용한다. 본 시스템은 규칙기반 시스템이므로 대용량의 발음열 사전이나 음소열 사전을 필요로 하지 않고 문서 기반 형태소 분석기를 그대로 이용할 수 있다는 이점이 있다.

• 말소리와 음성과학
• /
• 제8권4호
• /
• pp.103-113
• /
• 2016

This paper aims to propose articulatory features as novel predictors for automatic pronunciation assessment of English produced by Korean learners. Based on the distinctive feature theory, where phonemes are represented as a set of articulatory/phonetic properties, we propose articulatory Goodness-Of-Pronunciation(aGOP) features in terms of the corresponding articulatory attributes, such as nasal, sonorant, anterior, etc. An English speech corpus spoken by Korean learners is used in the assessment modeling. In our system, learners' speech is forced aligned and recognized by using the acoustic and pronunciation models derived from the WSJ corpus (native North American speech) and the CMU pronouncing dictionary, respectively. In order to compute aGOP features, articulatory models are trained for the corresponding articulatory attributes. In addition to the proposed features, various features which are divided into four categories such as RATE, SEGMENT, SILENCE, and GOP are applied as a baseline. In order to enhance the assessment modeling performance and investigate the weights of the salient features, relevant features are extracted by using Best Subset Selection(BSS). The results show that the proposed model using aGOP features outperform the baseline. In addition, analysis of relevant features extracted by BSS reveals that the selected aGOP features represent the salient variations of Korean learners of English. The results are expected to be effective for automatic pronunciation error detection, as well.