• Journal of Convergence for Information Technology
• /
• 제9권8호
• /
• pp.1-8
• /
• 2019

Dialog system is becoming a new dominant interaction way between human and computer. It allows people to be provided with various services through natural language. The dialog system has a common structure of a pipeline consisting of several modules (e.g., speech recognition, natural language understanding, and dialog management). In this paper, we tackle a task of domain classification for the natural language understanding module by employing machine learning models such as convolutional neural network and random forest. For our dataset of seven service domains, we showed that the random forest model achieved the best performance (F1 score 0.97). As a future work, we will keep finding a better approach for domain classification by investigating other machine learning models.

• The Journal of Korean Physical Therapy
• /
• 제12권3호
• /
• pp.293-310
• /
• 2000

This study was performed to investigate rehabilitation service patterns of stroke patients in metropolis of Korea. Seoul, Taegu. Taejon, Pusan and Kwangju from April-July. 2000. Authors developed questionnair, and distributed it to each physical therapist. Total number of distributed questionnaire was 800, and 622 questionnaire were collected and analysed. 1. The occurrence rate of ischemic stroke$(51.1\%)$ was higher than hemorrage stroke$(48.9\%)$. The highest incidence of the stroke was noted in the group or60 years and ratio of male to female 1.3:1 2. The several warning sign is motor deficit$(50.3\%)$, headache. dizziness. vomitting$(32.6\%)$ and difficulty speaking or understanding$(8.2\%)$. 3. The most important contributing factor of stroke was hypertension both hemorrage stroke$(50.7\%)$ and ischemic stroke$(47.2\%)$. 4. In the painful stroke patients$(53.4\%)$, the major problems were shoulder pain$(55.1\%)$ and shoulder-hand syndrome$(31.9\%)$. There is no clinical method for relieving the pain. 5. The seasonal preference was winter and autumn followed by summer and spring in regardless of diagnosis. 6. In the surgery, hemorrage stroke$(61.2\%)$ was higher than ischemic stroke$(13.5\%)$. 7. The major associated impairment were motor deficit$(99.0\%)$, hearing and speech deficit$(30.9\%)$.perception deficit$(15.9\%)$. psychological deficit$(14.1\%)$ and vision deficit$(10.6\%)$. We need more role of speech pathologist and psychotherapist. 8. The rehabilitation services for stroke patients were given only $15\%$ by onset. 9. Medical doctor did not checking everyday$(41\%)$. 10. Patents said that the physical therapist well understanding$(60.1\%)$ than medical doctor$(36.2\%)$ about their conditions.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• 제30권2호
• /
• pp.95-100
• /
• 2019

Background and Objectives For patients with polyps and cysts, glottal gaps resulting from their lesions have negative respiratory effects when they vocalize. Phonatory Aerodynamic System is clinically used, but is often limited in the measurement of vowels. So the researchers attempted to verify the usefulness of Phonatory Aerodynamic System by comparing differences in respiratory characteristics and patterns which can be measured by the level of connected speech. Materials and Method Among the subjects who were diagnosed through a stroboscopy, there were 33 patients with polyps and 23 patients with cysts. Then, 36 subjects who were found to have no specific findings through a stroboscopy and perceptual test were selected to the normal group. We compared respiratory characteristics and patterns. And compared vocal polyps and cysts before and after laryngeal micro surgery (LMS). Results First, difference in respiratory patterns between the normal group and the patients with polyps and cysts were examined to show that breath groups, breath group syllables, and expiratory·inspiratory volume were significantly higher in the polyp/cyst group than those in the normal group, indicating that precision was lowered during the conversation, due to reduction in speech intelligibility and interruption of communication. Second, there were significant differences in maximum phonation time, mean flow rate, and subglottal pressure among respiratory characteristics, breath groups, breath group syllables, and inspiratory volume before and after LMS, which appeared to be similar to the normal group. Conclusion The understanding of respiratory characteristics and patterns produced by patients in connected speech which is most similar to natural speech was found to be the objective and useful method for examining characteristics of the subjects.

• Speech Sciences
• /
• 제11권1호
• /
• pp.131-145
• /
• 2004

The informative or important entities in utterances are focused and the focused items are usually accompanied by changes in phonetic manifestation. Phonetic realizations triggered by focus include changes of tonal contours as well as segmental strengthening. Focus in Korean is characterized by new phrase initiation, dephrasing, and initial tone contour with an enlarged pitch range in addition to segmentally lengthened initial segment. Focusing on the prosodic cues which play an important role in delivering the speakers' intention, this study aims to find out what intonational characteristics of Korean focus are realized by English learners of Korean. The English learners are divided into two groups according to their fluency in Korean, and the differences in focus realization between each group are discussed. Furthermore, the phonological and phonetic realizations of focus by English learners of Korean are compared to those by Korean native speakers. The results of this study yields two suggestions for Korean intonation education of L2 learners. First, the comparison between the two speaker groups can give better understanding in how and why the Korean intonation of English speakers is different from that of Koreans. Second, each phonological and phonetic characteristic of focus realization can weigh differently and its realization provides a criterion for evaluation of L2 Korean proficiency.

• Phonetics and Speech Sciences
• /
• 제6권4호
• /
• pp.17-26
• /
• 2014

The present study examined epenthetic vowels produced by Korean learners of English in read sentences, in terms of acoustic measures and extra-phonological factors. The results demonstrated three main findings. First, epenthetic vowels had relatively high F1 values and a wide range of F2 values. Most of the epenthetic vowels were inserted near Korean high central vowels, but some vowels were inserted near front vowels due to co-articulation with surrounding vowels. Second, vowel epenthesis was affected by the context. The results showed that the epenthesis was frequently seen with word junctions between obstruents (e.g., stops-fricatives). Third, Korean learners were not affected by English background and were very weakly affected by orthography. English experience, which is one of the extra-phonological factors, was not related to epenthesis production. However, orthography, the other extra-phonological factor, very weakly affected the amount of epenthesis production. Nine percent of all epenthesis production was affected by the English past-tense suffix '-ed'; approximately 70% of the participants were affected by this suffix. The findings of the present study contributed to understanding vowel epenthesis. First, the study revealed that the epenthetic vowels produced by Korean learners of English were close to the high central vowel, supporting previous studies that the epenthetic vowel is quite close to the shortest vowel. Second, the study examined the various phonetic environments of epenthetic vowels, revealing that vowel epenthesis occurred more frequently in a certain phonetic circumstance.

• Phonetics and Speech Sciences
• /
• 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.

• The KIPS Transactions:PartB
• /
• 제15B권6호
• /
• pp.595-602
• /
• 2008

The focused word of each sentence is a help in recognizing and understanding spoken Korean. To find the method of focused word spotting at spoken speech signal, we made an analysis of the average and variance of Fundamental Frequency and the average energy extracted from a focused word and the other words in a sentence by experiments with the speech data from 100 spoken sentences. The result showed that focused words have either higher relative average F0 or higher relative variances of F0 than other words. Our findings are to make a contribution to getting prosodic characteristics of spoken Korean and keyword extraction based on natural language processing.

• Speech Sciences
• /
• 제13권3호
• /
• pp.207-219
• /
• 2006

The present study was designed to investigate the comprehension of 'who' and 'what' questions in 2- to 3-year-old normal children. Sixty children were divided into 3 groups depending on their ages, i.e., age groups 2;6-2;11, 3;0-3:5, and 3;6-3;11. Three types of 'who' questions and 2 types of 'what' questions were generated depending on the attached case markers, i.e., who-nominative, who-accusative, who-dative, what-nominative, and what-accusative. The children watched 36 cuts of short video recordings. After watching each cut, they were asked to answer one of the 5 types of wh-questions. For the 'who-nominative' and 'what-accusative' questions, even the late 2-year-old children performed with over 70% of accuracy, and the late 3-year-old children performed with over 95% of accuracy. For the 'who-accusative' and 'who-dative' questions, the late 2-year olds exhibited difficulty in comprehension with performance accuracy of 41% and 33%, respectively. However, the late 3-year olds could comprehend those questions correctly with over 90% of accuracy. On the other hand, in answering 'what-nominative' questions, the children did not show rapid development across the age groups, as the mean performance accuracies of the 3 groups were 39%, 49%, and 59%, respectively. The results indicated that children's understanding of a wh- question is largely affected by the case of the interrogative.

• Phonetics and Speech Sciences
• /
• 제2권4호
• /
• pp.19-28
• /
• 2010

The purpose of this study was to increase the current understanding of the acoustic characteristics of voices with advancing age. The relationship between age-related changes in body physiology and certain acoustic characteristics of voice was studied in a sample of 80 men representing four chronological age groupings (20-29, 50-59, 60-69, 70-79) who were all of good physical condition. Each subject was asked to phonate the vowel /a/, /i/, and /u/ for as long as possible at comfortable frequency and intensity level and read the sentence. A promising voice analysis program (Multi-Dimensional Voice $Program^{TM}$) was used to measure the fundamental frequency ($f_0$), jitter, shimmer, $f_0$ variation, peak-amplitude variation, smoothed pitch perturbation quotient, smoothed amplitude perturbation quotient, soft phonation index, $f_0$-tremor intensity index, amplitude tremor intensity index, and noise-to-harmonics ratio from the samples.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1777-1778
• /
• 2007

In this paper, We design and implement a humanoid robot, With Educational purpose, which can collaborate and communicate with human. We present an affective human-robot communication system for a humanoid robot, D2, which we designed to communicate with a human through dialogue. D2 communicates with humans by understanding and expressing emotion using facial expressions, voice, gestures and posture. Interaction between a human and a robot is made possible through our affective communication framework. The framework enables a robot to catch the emotional status of the user and to respond appropriately. As a result, the robot can engage in a natural dialogue with a human. According to the aim to be interacted with a human for voice, gestures and posture, the developed Educational humanoid robot consists of upper body, two arms, wheeled mobile platform and control hardware including vision and speech capability and various control boards such as motion control boards, signal processing board proceeding several types of sensors. Using the Educational humanoid robot D2, we have presented the successful demonstrations which consist of manipulation task with two arms, tracking objects using the vision system, and communication with human by the emotional interface, the synthesized speeches, and the recognition of speech commands.