• 음성과학
• /
• 제12권3호
• /
• pp.185-200
• /
• 2005

The objective of this study is to examine acoustic cues in spoken French for the assessment of pronunciation which is necessary to realization of the multimedia system. The corpus is composed of simple expressions which consist of the French phonological system include all phonemes. This experiment was made on 4 male and female French native speakers and on 20 Korean speakers, university students who had learned the French language more than two years. We analyzed the recorded data by using spectrograph and measured comparative features by the numerical values. First of all, we found the mean and the deviation of all phonemes, and then chose features which had high error frequency and great differences between French and Korean pronunciations. The selected data were simplified and compared among them. After we judged whether the problems of pronunciation in each Korean speaker were either the utterance mistake or the interference of mother tongue, in terms of articulatory and auditory aspects, we tried to find acoustic features as simplified as possible. From this experiment, we could extract acoustic cues for the construction of the French pronunciation training system.

• 대한음성학회지:말소리
• /
• 제46호
• /
• pp.87-102
• /
• 2003

In this paper, we present an English pronunciation correction system for Korean speakers and show some of experimental results on it. The aim of the system is to detect mispronounced phonemes in spoken words and to give appropriate correction comments to users. There are several English pronunciation correction systems adopting speech recognition technology, however, most of them use conventional speech recognition engines. From this reason, they could not give phoneme based correction comments to users. In our system, we build two kinds of phoneme models: standard native speaker models and Korean's error models. We also design recognition network based on phonemes to detect Koreans' common mispronunciations. We get 90% detection rate in insertion/deletion/replacement of phonemes, but we cannot get high detection rate in diphthong split and accents.

• 말소리와 음성과학
• /
• 제3권2호
• /
• pp.3-10
• /
• 2011

This study investigates the role of suprasegmental features with respect to the intelligibility of Korean-spoken English judged by Korean and English raters as being good or bad. It has been hypothesized that Korean raters would have different evaluations from English native raters and that the effect may vary depending on the types of suprasegmental factors. Four Korean and four English native raters, respectively, took part in the evaluation of 14 Korean subjects' English speaking. The subjects read a given paragraph. The results show that the evaluation for 'intelligibility' is different for the two groups and that the difference comes from their perception of L2 English suprasegmentals.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제26권4호
• /
• pp.414-421
• /
• 2000

The objective evaluation of velopharyngeal closure function is the key to diagnosis and therapy control of velopharyngeal incompetency. The aim of this study is to evaluate the aerodynamic and acoustic characteristics of the velopharyngeal closure function of patients who have developed velopharyngeal incompetency after management with speech aids. The test words were composed of sustained vowels /a/, /i/, /e/, /u/, /ja/, /je/, /wi/ and polysyllabic words /p'ap'i/, /siso/, /mami/ for measuring nasalance, The data was collected before the placement of the speech aids and one to three months after. The results were as follows: The nasalance score of the velopharyngeal incompetency speakers was higher than that of the normal control group, except for nasal sounds, and was decreased after placement of the speech aids, especially in high vowels /i/ (P<.01) and /wi/ (P<.05).

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 10월 학술대회지
• /
• pp.83-88
• /
• 2003

This study carried out an experimental English pronunciation assessment to see the differences in the relationship between the different rater categories. The result shows that i) correlation between Korean and Native American raters is high(r=.98) enough to be considered reliable, ii) previous instructions about assessment rubric and the knowledge about English phonetics and phonology exert little influence on the rating scores, iii) correlation between the automatic ILT(Interactive Language Tutor) rating using speech recognition technology and Natives' rating is stronger than that between ILT and Koreans' rating.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1998년도 제15회 음성통신 및 신호처리 워크샵(KSCSP 98 15권1호)
• /
• pp.267-271
• /
• 1998

신경망에 의한 음절과 연속음성 인식시 동특성처리의 한방법으로 회귀신경망을 이용한다. 본 연구는 비회귀형 상위은닉층과 회귀형 하위은닉층을 가진 4층 구조의 다층회귀신경망으로 예측기를 반들어 나성화자 5명이 CV형 음절 14개, CVC형 음절 14개를 각각 5회씩 발음한 총 700개의 음성중 3회분인 420개 음성으로 학습한 후 나머지 2회분인 280개 음성으로 인식을 평가한다. 입력신호의 예측차수와 상, 하위 은닉층으 뉴런수를 변경시키면서 각각의 인식률을 조사해 본 결과 상위 은닉층의 뉴런이 10개이고 하위 은닉층의 뉴런이 10개와 15개 그리고 예측차수가 3,4차일 때 가장 양호한 인식기로 동작한다는 것을 알 수 있었다. 이 때 나타난 인식률은 Elman 망보다 다소 우세하다.

• 한국음향학회지
• /
• 제17권6호
• /
• pp.43-53
• /
• 1998

본 논문에서는 한국어 TTS시스템을 위한 운율구 추출, 운율구 사이의 휴지 기간, 음소의 지속 시간 모델링 방법을 설명한다. 실험을 위해 여러 장르로 구성된 400문장을 선 정하고, 이를 전문 여성 아나운서가 발성하였다. 녹음된 음성 신호에 대해 음소 및 운율구 경계를 결정하고, 문장에 대해서는 형태소 분석, 발음표기 변환, 구문 분석을 수행하였다. 400문장(약33분) 중 240문장(약20분)을 이용하여 결정 트리 및 회귀 트리를 학습시킨 후, 160분장(약13분)에 대해 실험하였다. 운율 모델링을 위한 특징들이 제안되었고, 학습된 트리 들을 해석함으로써 특징들의 유효성이 평가되었다. 실험 문장에 대해 운율구 경계의 유무를 결정하는 결정 트리의 오류율은 14.46%이었고, 운율구 사이의 휴지 기간과 음소 지속 시간 을 예측하기 위한 회귀 트리들의 평균 제곱 오류근(RMSE)이 각각 132msec, 22msec이었다. 수집된 모든 자료(400문장)로 학습한 결과, 운율구 경계 결정 오류율, 휴지 기간 및 지속시 간 RMSE의 10-fold cross-validation 추정치가 각각 13.77%, 127.91msec, 21.54msec이었다.

• 말소리와 음성과학
• /
• 제6권4호
• /
• pp.101-108
• /
• 2014

This study investigates the effects of Japanese learners' Korean segmental production on pronunciation evaluation by Korean native raters. Read speech from 24 learners whose native language is Japanese are transcribed at the phonemic level, and confusion matrices are generated based on the phonemic transcriptions. The deviance from the canonical pronunciation found in the learners' speech is analyzed in terms of phoneme substitutions, vowel insertions, and consonant deletions. Each learner's pronunciation is rated impressionistically by 5 Korean native raters. The result shows that the deviance from the canonical pronunciation is strongly correlated with the pronunciation evaluation scores. Especially, the rates of phoneme substitutions and vowel insertions which are very strongly correlated with the pronunciation evaluation scores.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2001년도 봄 학술발표논문집 Vol.28 No.1 (B)
• /
• pp.592-594
• /
• 2001

본 연구에서는 음성인식에 있어서 음향모델의 고정도화를 위해 통계적 방법인 HMM과 시간동기형 Viterbi 알고리즘을 기반으로 한 세그멘트되지 않은 음성의 자동 세그멘테이션에 관한 연구를 수행하였다. 본 연구에서는 소량의 세그멘트된 음성에 대해 연속분포형 HMM 기본모델을 작성한 후 이를 표준패턴으로 사용하고, 세그멘트되지 않은 입력음성의 특징 피라미터에 대해 시간동기형 Viterbi 알고리즘의 프레임마다 최대가 되는 지점을 최적경계로 설정하고, 앞에서 구현 최적 경계 정보와 언어학적 지식인 발음사전 정보를 이용하여 음성을 세그멘테이션 하는 것이다. 본 연구와의 비교를 위해 HTK를 이용하여 위와 동일한 과정을 수행하였다. 이렇게 구한 음성의 세그멘테이션 정보를 이용하여 연속분포형 HMM 기본모델과 HTK의 CHMM 기본모델을 각각 작성한 후, 국어공학센터(KLE) 단어 데이터에 대해 단어인식 성능을 평가하였다. 실험결과, KLE 452 남성과 여성에 대해, 본 연구실 인식 시스템은 화자독립 단어인식률 89.4%, 85.1%, HTK의 화자독립 단어인식률 85.1%, 81.9%를 각각 얻었다.

• 말소리와 음성과학
• /
• 제4권4호
• /
• pp.37-43
• /
• 2012

This study investigates an independent evaluation of prosody and segmentals with reference to the difference in the foreign accent of Korean, Chinese, and Japanese learners of English. For this study, a set of stimuli were made of English sentences read by male and female Korean, Chinese, and Japanese learners of English by prosody swapping technique. Two groups of American and Korean subjects evaluated the difference in the prosody and segmentals of the stimuli by pairwise difference rating. The results showed that there was no significant difference in the evaluation scores of prosody and segmentals across accents for either subject group. The results also showed that both subject groups indicated a greater score with segmentals than with prosody. The results of the present study are significant in that they are opposite to the claim of some previous studies that prosodic factors could have a greater influence on the foreign accent and intelligibility than segmentals.