• Phonetics and Speech Sciences
• /
• v.11 no.3
• /
• pp.9-21
• /
• 2019

This study aimed to compare the prosodic characteristics of North Korean defectors and South Koreans in three types of sentences (declarative, interrogative, and negative) in two reading tasks (short and dialogue) through acoustic analysis and auditory-perceptual evaluation. In addition, this study examined the relationship between the auditory-perceptual evaluation scores and self-assessment questionnaires on intonation for North Korean defectors. The participants were 15 North Korean defectors and 15 Korean speakers with standard Seoul accents. For statistical analysis, three-way mixed ANOVA and multivariate analysis were performed within the three types of sentences in the reading tasks through acoustic analysis and the Mann-Whitney U Test for auditory-perceptual evaluation. Pearson's product-moment correlation coefficients were also used to identify the correlations between the results of the self-assessment questionnaire on intonation and the auditory-perceptual evaluation. The North Korean defectors were found to have a significantly lower pitch range and auditory-perceptual evaluation score than South Koreans in reading tasks. Moreover, there was a significant correlation between their auditory-perceptual evaluations and self-assessment questionnaires on intonation. The study findings suggest that North Korean defectors, who face many challenges with intonation, showed a tendency to think that their intonation differed from the standard Korean intonation and showed better auditory evaluation results for interrogative sentences.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.289-294
• /
• 2022

의존구문분석은 문장을 의존관계(의존소-지배소)로 분석하는 구문분석 방법론이다. 현재 사전학습모델을 사용한 전이 학습의 딥러닝이 좋은 성능을 보이며 많이 연구되지만, 데이터셋에 의존적이며 그로 인한 자료부족 문제와 과적합의 문제가 발생한다는 단점이 있다. 본 논문에서는 언어학적 지식에 기반한 강화된 지배소-의존소 제약규칙 에지 알고리즘을 심층학습과 결합한 모델을 제안한다. TTAS 표준 가이드라인 기반 모두의 말뭉치로 평가한 결과, 최대 UAS 96.28, LAS 93.19의 성능을 보였으며, 선행연구 대비 UAS 2.21%, LAS 1.84%의 향상된 결과를 보였다. 또한 적은 데이터셋으로 학습했음에도 8배 많은 데이터셋 학습모델 대비 UAS 0.95%의 향상과 11배 빠른 학습 시간을 보였다. 이를 통해 심층학습과 언어지식의 결합이 딥러닝의 문제점을 해결할 수 있음을 확인하였다.

• Korean Journal of Psychosomatic Medicine
• /
• v.24 no.2
• /
• pp.165-173
• /
• 2016

Objectives : Since the awareness of autism spectrum disorders(ASD) is growing, as a result, it is increasing numbers of infants and toddlers being referred to specialized clinics for a differential diagnosis and the importance of early autism spectrum disorders detection is emphasized. This study is to know the difference between ASD and intellectual disability(ID) from comparison of the demographics, clinical characters and obstetric complications. Methods : The participants are 816 toddlers who visited the developmental delay clinic(DDC) in National Health Insurance Ilsan hospital. The number of toddlers diagnosed as ASD and ID was 324 and 492. 75 toddlers out of 114 who returned to DDC were diagnosed as ID at the first visit but 7 of them had changed diagnosis to ASD at the second visit. After compared ASD with ID from the first visit, we analyzed characters of toddlers who had the changed diagnosis to ASD at the second visit. Results : As a result, the comparison between ASD and ID at the first visit shows that the boys have higher ratio, lower obstetric complication and lower language assessment score in ASD. The toddlers who had the changed diagnosis at the second visit were all boys and they had more cases of family history of developmental delay and had lower score of receptive language developmental quotient. Conclusions : These findings suggest that sex, language characteristics and obstetric complication could be useful in the early detection of ASD.

• Phonetics and Speech Sciences
• /
• v.16 no.3
• /
• pp.71-78
• /
• 2024

This study aimed to establish evaluation methods for the speech processing stages of phonological encoding, phonological short-term memory, and articulation transcoding from a psycholinguistic perspective. A meta-analysis of 21 studies published between 2000 and 2024, involving 1,442 participants, was conducted. Participants were divided into six groups: general, dyslexia, speech sound disorder, language delay, apraxia+aphasia, and childhood apraxia of speech. The analysis revealed effect sizes of g=.46 for phonological encoding errors, g=.57 for phonological short-term memory errors, and g=.63 for articulation transition errors. These results suggest that substitution errors, order and repetition errors, and phoneme addition and voicing substitution errors are key indicators for assessing these abilities. This study contributes to a comprehensive understanding of speech and language disorders by providing a methodological framework for evaluating speech processing stages and a detailed analysis of error characteristics. Future research should involve non-word repetition tasks across various speech and language disorder groups to further validate these methods, offering valuable data for the assessment and treatment of these disorders.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.1
• /
• pp.9-14
• /
• 2017

Preschool children to do production and acquisition of phonological system from birth to 8 years of age. If a child has hearing loss, he/she has a lot of difficulties to hear sound. The problem of auditory perception can causes limited speech acquisition, delayed language development, and communication disorders. It also affects learning, social and emotional development. Early detection and diagnosis of hearing loss are important for intervention. However, it may be difficult to detect if the degree of hearing loss are slight and/or it appears only on some frequencies. In cases of these kinds of hearing losses, it is often difficult to provide aural intervention. The goal of this study is to discuss the interpretation of audiological evaluation in case of mild-to-moderately severe asymmetric ski-slop sensorineural hearing loss, analyze communication problems, and concerning about audiological, and speech-language pathological rehabilitation.

• Phonetics and Speech Sciences
• /
• v.13 no.3
• /
• pp.1-13
• /
• 2021

This study examined the characteristics of linguistic prosody in terms of cerebral lateralization in three groups of 9 healthy speakers and 14 speakers with a history of stroke (7 with left hemisphere damage (LHD), 7 with right hemisphere damage (RHD)). Specifically, prosodic characteristics related to speech rate, duration, pitch, and intensity were examined in three types of interrogative sentences (wh-questions, yes-no questions, alternative questions) with auditory perceptual evaluation. As a result, the statistically significant key variables showed flaws in production of the linguistic prosody in the speakers with LHD. The statistically significant variables were more insufficiently produced for wh-questions than for yes-no and alternative questions. This trend was particularly noticeable in variables related to pitch and speech rate. This result suggests that when Korean speakers process linguistic prosody, such as that of lexico-semantic and syntactic information in interrogative sentences, the left hemisphere seems to be superior to the right hemisphere.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.74-81
• /
• 1995

This paper describes the development of speech databases for the Korean language which were constructed at Communications Research Laboratory in KAIST. The procedure and environment to construct the speech database are presented in detail, and the phonetic and linguistic properties of the databases are presented. the databases were intended for use in designing and evaluating speech recognition algorithms. The databases consist of five different sets of speech contents : trade-related continuous speech with 3,000 words, variable-length connected digits, phoneme-balanced 75 isolated words, 500 isolated Korean provincial names, and Korean A-set words.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• 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.

• Proceedings of the KSLP Conference
• /
• 2003.11a
• /
• pp.137-137
• /
• 2003

본 연구는 직업적 음성 사용자인 연극 배우의 음성 관리, 극중 인물 특징을 표현하기 위한 요소 중 음성이 차지하는 비중과 적합한 발성 및 발화 방법에 대하여 살펴보았다. 본 연구에는 대구광역시 소재 K극예술연구회의 연극 배우 9명이 참여하였다. 연극 배우의 음성 관리 및 극중 인물의 특성을 표현하기 위한 발성 및 발화 방법에 대한 설문지를 작성하여 조사하였다. 여러 가지 인물에 적합한 발성법으로 '산책' 문단을 발화하도록 한 뒤, 대상자들에게 각 인물에 대한 발성 방법을 설문지에 기록하도록 하였다. 대상자들이 발화한 음성 샘플을 음향학적, 지각적 측면에서 평가하여 대상자들이 기술한 발성 및 발화 방범과의 상관을 살펴보았다. 음성 샘플은 Windows용 Praat(4.1.7)으로 수집 및 분석하였다. (중략)

• Proceedings of the KSLP Conference
• /
• 1996.11a
• /
• pp.79-79
• /
• 1996

최근 들어 음성에 대한 일반인들의 관심이 높아지면서 음성이상을 호소하며 이비인후과 외래를 방문하는 환자가 점차적으로 증가하는 추세에 있다. 그러나 이러한 음성이상을 객관적으로 평가할 수 있는 기준이 국내에는 거의 없는 실정이다. 이에 저자들은 본 연구에서 기왕력 상 폐질환이나 신경계질환, 후두질환을 앓은 적이 없으며 음성조율 기관에 이상이 없고 정상적인 청력을 가진 10세에서 69세까지의 무작위 추출된 정상 한국인 남자 112명과 여자 122명을 대상으로 Aerophone II voice function analyzer를 이용하여 공기역동학적 검사 중 최대발성지속시간(maximum phonation time), 평균호기류율(mean airflow rate), 발성율(phonation quotient), 발성시 기류량(phonatory flow volume) 및 성문하압(subglottal pressure)의 정상 한국인의 남녀 년령별 평균치를 측정하고자 하였다. (중략)