• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.634-636
• /
• 2018

최근 들어 Big Data를 활용한 기술들이 많이 개발되고 있다. 본 연구에서는 Machine Learning과 Deep Learning을 이용하여 음성 Big Data를 활용한 이미지 시각화를 통해 보이스 피싱 등 여러 범죄에 도움이 되게 하고 그 외의 음성과 얼굴 매칭을 통한 새로운 보안시스템 및 다양한 시너지 효과들을 기대하는 서비스를 기술한다.

• Journal of Distribution Science
• /
• v.14 no.9
• /
• pp.95-110
• /
• 2016

Purpose - Based on expectation-disconfirmation theory, this study attempted to fill the gap in the literature by treating the expected profitability as a moderator in the relationship between these constructs, identifying what instrumental factors have effects on dissatisfaction, in turn lead to exit intention, neglect, voice, and loyalty, and provide the managerial implications for building long-term relationship to enhance the partnership between franchisor and franchisee. Research design, data and methodology - In order to test the hypotheses, the authors developed several hypotheses. The data were collected from 254 franchisees in Seoul and Gyeonggi Province with SPSS 18.0 and SmartPLS 2.0. Results - The findings of the study are as follows. First, marketing support and competitiveness of product and service had a negative effect on dissatisfaction, but did not on logistics support. Second, franchisee dissatisfaction had a positive effect on exit intention and neglect, and had a negative effect on loyalty. However, franchisee dissatisfaction had not a significant effect on voice. Third, expected profits play a moderating role in the relationships between marketing support, competitiveness of product and service and dissatisfaction, between dissatisfaction and exit intention, voice, loyalty, and neglect. First, marketing support and competitiveness of product and service were found to have a greater influence on dissatisfaction for the low expected profitability group than the highly expected profitability group. Also, dissatisfaction had a greater impact on exit intention, voice, and neglect for the low expected profitability group than the high expected profitability group while dissatisfaction had a weaker impact on loyalty for high expected profitability group. Conclusions - The result of this study indicates that franchisors should reduce dissatisfaction and prevent or improve complaint behaviors by continuously identifying the impact relationship between franchisee dissatisfaction and decision factors caused by difference in expectations for roles of franchisees and franchisors. In addition, franchisors should acknowledge that the impacts of marketing support, and product and service competitiveness on franchisee dissatisfaction and on exit intention, neglect, and loyalty differ by expected profits. Therefore they should provide support in perceiving high expected profits through creating direct profits including high sales, low costs, and low rents.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.8 no.1
• /
• pp.27-32
• /
• 1997

Recently, many people suffering from voice color change visit otolaryngologist. There is no specific data which can be evaluated objectively for voice color change in korean. In aerodynamic study, maximum phonation time, mean air flow rate, phonatory flow volume and subglottal pressure were tested by using Aerophone II voice function analyzer in korean. 112 male and 122 female aged from 10 to 69 years were randomly selected. Maximum phonation time was 20.8${\pm}$6.4sec in male and 17.2${\pm}$4.1sec in female. Mean air flow rate was 167.1${\pm}$61.4ml/sec. in male and 129.6${\pm}$49.3ml/sec in female. Phonatory flow volume was 3184.5${\pm}$646.0ml in male and 2122.1${\pm}$670.5ml in female. Subglottal pressure was 4.1${\pm}$1.8 cmH2O in male and 3.5${\pm}$1.4cm $H_2O$ in female. There was no statistically significant difference among age groups in all above results.

• Journal of Sensor Science and Technology
• /
• v.22 no.2
• /
• pp.156-161
• /
• 2013

This study was aimed to implement the electroglottography (EGG) system for analyzing fundamental frequency of the phonation. EGG was recorded from the conductance between ring electrodes attached to the neck skin area near thyroid cartilage with high frequency carrier electric signals during vocalization, and voice signal was recorded with microphone simultaneously. EGG and voice signals were transmitted to the audio port in PC and recorded with stereo sound recording program. From the digitized data, several parameters such as pitch, jitter, shimmer, CQ and SQ were analyzed from the vowel sounds. For the voice training, sound fundamental frequency was displayed during the vocalization and singing a song using pitches analyzed from the EGG. The system implemented in this study could be used for vocal exercise.

• Child Health Nursing Research
• /
• v.15 no.3
• /
• pp.261-270
• /
• 2009

Purpose: The purpose of this study was to compare the result of one-way ANOVA with that of cross-correlation time series analysis in order to evaluate physiologic responses of premature infants to human voices. Methods: Four premature infants born prior to 32 weeks gestational age were included in the study. The Gould 4000TA Recording System recorded the preterm infant's heart and respiratory rate while they were listening to a pre-recorded voice recording. Each infant listened to both male and female voices (1 min each) at each testing session. Results: The results of both one-wayANOVA and cross-correlation time series analysis using heart and respiratory rate data were not consistent in some of premature infants. A cross-correlation time series analysis revealed that the responses of premature infant to vocal stimulation occurred at a varying number of seconds after the stimulus was presented and lasted for over 20-30 sec. Conclusion: The results indicate that a time series analysis can provide more detailed information on the rapidly changing physiologic status of premature infant to the auditory stimulus. In addition, the results provide an insight into an auditory responsitivity of premature infants to a naturally occurring sound, the human voice, in the neonatal intensive care unit.

• The Korean Journal of Emergency Medical Services
• /
• v.16 no.2
• /
• pp.31-41
• /
• 2012

Purpose : The purpose of the present study is to analyze the accuracy and fatigue felt by lay persons receiving CPR training when they perform hands only CPR (HOCPR) and traditional CPR (TCPR). The performance of CPR data will provide the criteria of dispatcher guidelines for the general public. Methods : For 2 minutes duration, HOCPR was conducted by 51 subjects and TCPR was conducted by 48 subjects. The accuracy measurement of chest compressions was based on the 2010 AHA guideline; the subjective fatigue level in before and after experiment was measured by a self-administered questionnaire. Results : There were no significant differences between the average depth, chest compression depth and chest compression location in terms of chest compression accuracy. However, there were significant differences between the two experimental groups in the accuracies for average speed and chest compression speed. The subjective fatigue level showed no significant difference. Conclusion : The experimental group performing HOCPR showed more accurate compression speed and lower fatigue level. These results suggested that HOCPR would be more effective in training the lay persons in accordance with the voice-instructed CPR.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.758-761
• /
• 2002

Voice of U(VoIP) technology Provides voice service as well as data service via Internet. It has been a promising technology as Internet grows fast and the requirements are increasing. Recently, serveral protocols have been created to allow telephone calls to be made over IP networks, notably, SIP and H.323. Due to introducing SIP and H.323, There are many change at internet telephony service. Internet telephony enables a wealth of new service possibility Users can control telephony service directly. In this paper, we design and implementation CPL client based on SIP system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.442-444
• /
• 2013

In this paper, we may by gestures and voice, to know the effect of imitation on the life. Measuring how much about what is imitation unconsciously during conversation to collect data for measuring mimic such speak a short (1 sec) words. It can be used as a basis to predict the outcome of the interview further. Even used as a basis to predict future outcomes. We expect that our group and other researchers will continue to pursue this analysis with larger datasets and across different demographics.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.5
• /
• pp.842-856
• /
• 1994

The various services that a broadband integrated services digital network (B-ISDN) carries, have a wide range of delay, delay jitter and cell loss probability requirements. Design of appropriate control schemes for B-ISDN is an extremely important and challenging problem. In this paper, we proposed multiplexing algorithm with both delay and loss priorities in order to satisfy the diverse requirements. For the implementation of cell lose priority, we assumed that voice cells are generated as non-discardable(i.e., high priority) and discardable (i.e., low priotity)cells. The low priority voice cell may be discarded inside the network if congestion occurs. The cell dropping scheme is shown to reduce cell losses as well as delays for both voice and data. Such a load shedding scheme is expected to improve significantly utilization of B-ISDN.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2
• /
• pp.66-70
• /
• 1997

In order to obtain natural emotional voice in laboratory, an autobiographical recall method was used and happy, angry, sad and afraid feelings were induced in 16 college students. Three independent judges rated the subject's facial expressions and vocal characteristics. The mood induction results were compared with those from the actor-initiated method. Data analysis showed that recall-induced voices successfully conveyed subtle emotional cues, while actor-induced voices signaled more extreme emotioms. Implications of the autobiographical recall method in emotional voice research and potential problems are discussed.