• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.851-861
• /
• 1998

Korean language is to be characterized by the rich vocal sound variation. In order to increase the probability of vocal sound recognition and to provide a natural vocal sound synthesis, a systematic and thorough research into the characteristics of Korean language including its vocal sound changing rules is required. This paper addresses an effective way of vocal sound recognition and synthesis by providing the design and implementation of the Korean vocal sound variation rule. The regulation we followed for the design of the vocal sound variation rule is the Phonetic Standard(Section 30. Chapter 7) of the Korean Orthographic Standards. We have first factor out rules for each regulations, then grouped them into 27 groups for eaeh final-consonant. The Phonological Change Processing System suggested in the paper provides a fast processing ability for vocal sound variation by a single application of the rule. The contents of the process for information augmented to words or the stem of innected words are included in the rules. We believe that the Phonological Change Processing System will facilitate the vocal sound recognition and synthesis by the sentence. Also, this system may be referred as an example for similar research areas.

• Journal of Internet Computing and Services
• /
• v.5 no.6
• /
• pp.31-43
• /
• 2004

Voice over Internet Protocol (VoIP) is currently a popular research topic as a real time voice packet transmission method. But current Internet environment do not guarantee the quality of voice when we take a side view of delay, jitter and loss. Up to now, many voice based evaluation algorithms have been used to measure speech quality of VoIP systems. However, these algorithms have the defects that their results are different according to voice samples and some algorithms can not take network environment for speech transmission path. The E-model can be used to solve the problems of these algorithms. In this paper. we introduce VoIP planning guidelines through the various analysis of E-model which can model impairments of network quality as well as VoIP equipment quality systematically, We, also, show the evaluation method and results of speech transmission quality.

• The Journal of the Korea Contents Association
• /
• v.18 no.5
• /
• pp.311-318
• /
• 2018

This paper presents the artistic background and implementation structure of a conversational artificial intelligence interactive artwork, "An Evolving GAIA". Recent artworks based on artificial intelligence technology are introduced. Development of biomimetics and artificial life technology has burred differentiation of machine and human. In this paper, artworks presenting machine-life metaphor are shown, and the distinct implementation of conversation system is emphasized in detail. The artwork recognizes and follows the movement of audience using its eyes for natural interaction. It listens questions of the audience and replies appropriate answers by text-to-speech voice, using the conversation system implemented with an Android client in the artwork and a webserver based on the question-answering dictionary. The interaction gives to the audience discussion of meaning of life in large scale and draws sympathy for the artwork itself. The paper shows the mechanical structure, the implementation of conversational system of the artwork, and reaction of the audience which can be helpful to direct and make future artificial intelligence interactive artworks.

• Korean Journal of Cleft Lip And Palate
• /
• v.5 no.2
• /
• pp.95-108
• /
• 2002

언어 발달의 조기 단계를 이해하기 위한 일환으로 crying은 언어전 발달의 기초 단계로서 여러 학문적 분야에서 많은 연구가 있어왔다. 그러나 구순구개열(CLP))환아의 경우는cry-producing/control mechnism에 variation이 많은 이유로 이 분야의 연구는 거의 없는 실정이다. 이에 본 연구에서는 다음과 같은 의문점을 가지고 CLP환아의 cry feature에 대한분석을 하였다. 첫째, 정상아와 CLP환아의 cry에 전형적인 차이가 있는가? 둘째, CLP환아의 술전, 술후 cry feature에 변화가 있는가? 셋째, cry분석이 CLP환아의 이후 speech disorder에 대한 언어전 평가로서의 가치가 있는가? 넷째, 특정 parameter가 언어전 평가에 적절한 도구로 작용할 수 있는가? 생후 15개월 이내의 CLP 환아 3명과 유사한 나이대의 정상아 8명의 cry에 대한 공기역학 및 음향음성학적 분석을 통해 CLP 환아와 정상아, CLP환아의 술전, 술후 cry특성을 비교 분석하였다. 결과는 다음과 같다. 1 공기역학적 분석 1) airflow는 CLP 환아의 경우 정상아보다 약간 높았고 술 후 약간 증가하였다. 2)폐활량을 나타내는volume에서는 정상아보다 술전 CLP환자의 경우 보상적으로 더 큰 수치를 보였고 술후 약간 증가하였다. 3)강도를 나타내는 parameter(SPL)에서는 정상아 보다 술전 CLP환자의 계측치가 약간 작았으나 술 후 증가하는 양상을 보였다. 2. 음향음성학적 분석 1)기저 주파수 분석시 정상아에 비해 술 전 CLP환자의 경우 계측치가 약간 낮았으나 술 후 증가하여 정상군의 계측치에 근접하였다. 2)강도를 나타내는energy 측정시 정상아에 비해 술 전 CLP계측치가 보상성으로 약간 큰수치를 나타내었고 술 후 약간 더 증가하였다. 3) Shimmer에서는CUI환자의 술후계측치가술전에 비해 현저히 감소하여 정상군의 수치에 근접하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.1
• /
• pp.122-131
• /
• 2016

In the smart societies, such as the current unlike in the past, the voice that listeners will feel favor is changing through the development of ICT technologies and infrastructure. In other words, in the past, loud, intensive and fast voice is a favorite but now a new social and cultural situation that is changing them with ICT technologies. Now, this becomes one of the important things that we clarify 'Is it a voice that feels a favor?'. For this, in this paper, we identified what voice that listeners feel favor by applying ICT technologies. Studies were carried out to proceed largely divided into two categories. Firstly, as the quantified data, we extracted the impact on favorable feeling of listeners which related with emotional speech by empirical analysis work. To do this, we performed the experiment for the public. Secondly, we identified what kind of voice which listeners feel a good impression. For this, we identified voice characteristics that there are people who are influential in the real society. Also, we extracted both the voice characteristics of each influential people and common voice characteristics. In addition, we want to overcome the problems of qualitative methods that have originally limitations in objective respects which is significant to the voice analysis. For this, we performed the experiments of the voice analysis by numerical and visual approaches.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.530-536
• /
• 2021

Recently, due to the development of deep learning, end-to-end speech recognition, which directly maps graphemes to speech signals, shows good performance. Especially, among the end-to-end models, conformer shows the best performance. However end-to-end models only focuses on the probability of which grapheme will appear at the time. The decoding process uses a greedy search or beam search. This decoding method is easily affected by the final probability output by the model. In addition, the end-to-end models cannot use external pronunciation and language information due to structual problem. Therefore, in this paper conformer with lexicon transducer is proposed. We compare phoneme-based model with lexicon transducer and grapheme-based model with beam search. Test set is consist of words that do not appear in training data. The grapheme-based conformer with beam search shows 3.8 % of CER. The phoneme-based conformer with lexicon transducer shows 3.4 % of CER.

• Clinical and Experimental Pediatrics
• /
• v.45 no.10
• /
• pp.1199-1203
• /
• 2002

Purpose : The study aimed to evaluate the efficacy of auditory brainstem response(ABR) as a screening tool in children with speech and language disorders. Methods : Between January 1, 1999 and December 31, 2001, 139 patients with chief complaints of speech and language delay were recruited from the pediatric neurology clinic, Kyungpook National University Hospital, Daegu, Korea. They had ABR on entry and the clinical data were then analyzed. Results : Fifteen out of 139 cases(10.8%) showed abnormal findings; seven had pervasive developmental disorders, four had developmental language disorders, and four were noted to have other conditions. Among them, seven cases were noted to have conductive hearing loss and eight had sensoryneuronal hearing loss. We also evaluated the normal values in children at the ages of 18 months to seven years. The mean latency of wave I and V were $1.40{\pm}0.13$ and $5.57{\pm}0.26$ respectively. Interpeak latency of I-V was $4.18{\pm}0.24$. Conclusion : Based on these findings, ABR has proved to be a highly sensitive and specific index of hearing impairment. It should be used as a screening tool in children with speech and language disorders.

• The Journal of the Korea Contents Association
• /
• v.19 no.9
• /
• pp.262-270
• /
• 2019

This study aimed to develop designs for an early screening questionnaire for developmental disorders among children from multicultural families in the Republic of Korea, who are at an increased risk of developmental disorders due to cultural and language barriers. Research on early screening questionnaires for multicultural families is extremely scanty, unlike that on ordinary early detection tests designed for the same category of disorders. Worse still, there have been no attempts made at overcoming the limitations of language-based and intercultural communication that are endured by multicultural parents and social workers in the field. Given the challenges, this study confirmed through professional seminars the present status of early developmental disorder screening questionnaires and the necessity for developing specialized versions for multicultural children. Then the study identified the needs of the stakeholders by employing surveys and interviews, and obtained insights and core design elements. These preceding implementations led to the creation of an early developmental disorder screening questionnaire for multicultural families. The test kit incorporates the style of illustrations preferred by multicultural parents, as well as a system of language-specific interpretation services. Produced in a leaflet format, the questionnaire will be used at support centers for multicultural families and for disabled persons in each district for the practical purpose of early screening of developmental disorders among multicultural infants and preschool children.

• Journal of Gifted/Talented Education
• /
• v.22 no.2
• /
• pp.291-315
• /
• 2012

This study try to analyze feature of model creation and model developing process for gifted students and the activity of students and teachers affected those processes in scientific model constructing class for phase change of moon. For this, I teach scientific model constructing class for science gifted students. I shoot video and record the voice for whole class and each group activity, have a face-to-face talk for selected group members, analyze the paper of activities. I reconstruct model creation and model developing process for each groups and each students, draw a influence that activity aspects of the students and role of the teacher affected modelling process based on those data. After analyzing, I find that discussion in the group contribute model creation and model developing process and developing process of each model changed according to the similarity between target model and first model. The more the students actively participate group activities, the more first model is diversified and final model is more elaborated. Also, the teacher influence model creation and developing process.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.28-39
• /
• 2011

While the broadband multimedia technologies have been developing, the commercial market of digital contents has also been widely spreading. Most of all, digital cartoon market like internet cartoon has been rapidly large so video cartooning continuously has been researched because of lack and variety of cartoon. Until now, video cartooning system has been focused in non-photorealistic rendering and word balloon. But the meaningful frame extraction must take priority for cartooning system when applying in service. In this paper, we propose new automatic frame extraction method for video cartooning system. At frist, we separate video and audio from movie and extract features parameter like MFCC and ZCR from audio data. Audio signal is classified to speech, music and speech+music comparing with already trained audio data using GMM distributor. So we can set speech area. In the video case, we extract frame using general scene change detection method like histogram method and extract meaningful frames in the cartoon using face detection among the already extracted frames. After that, first of all existent face within speech area image transition frame extract automatically. Suitable frame about movie cartooning automatically extract that extraction image transition frame at continuable period of time domain.