• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.60-64
• /
• 1998

음성인식 시스템의 실용화 과정에서 훈련환경과 테스트 환경의 불일치로 인한 인식성능의 저하는 반드시 극복되어야 할 문제이다. 본 논문에서는 잡음 tR인 입력음성의 비음성구간에서 잡음레벨을 추정하여 음성 스펙트럼에서 추정된 잡음레벨을 빼는 스펙트럼 차감법고 스펙트럼 영역에서 미리 정해진 마스킹 레벨보다 낮은 에너지 값을 마스킹 레벨로 올려주는 잡음 마스킹을 함께 사용함으로써 훈련 환경과 테스트환경의 불일치를 줄이는 방법을 제안한다. 그리고 복수의 마스킹 레벨에 대한 모델들을 미리 만들어 두고 추정된 잡음 레벨에 따라 적합한 마스킹 레벨의 보델을 사용하여 인식을 수해？는 다중 모델 방법을 적용하였다. 자동차 소음환경에서 두 가지 마스킹 레벨에 대한 모델을 이용한 화자독립고립단어 인식 실험을 통하여 본 논문에서 제안한 방식은 정차중 무시동 환경에서 95.8%, 정차중 시동 환경에서 95.6%, 한적한 도로환경에서 92.8%, 복잡한 시내도로 환경에서 89.6%, 고속도로 환경에서 74.4%의 인식성능을 나타내었으며, 평균 90.7%의 성능을 얻을 수 있다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1996.10a
• /
• pp.76-79
• /
• 1996

본 논무에서는 한국어 음소를 대상으로 Kohonen 이 제안한 LVQ2 방법의 결저을 보완한 MLVQ2 방법으로 인식실험을 행하고 MLVQ2 알고리즘의 유효성을 검토하고자 한다. 인식실험을 위한 음성자료는 ETRI 611단어로부터 추출한 49음소를 사용하였다. 그리고 인식실험에 있어서는 먼저 파열음을 대상으로 학습회수, 표준패턴의 수, 샘플수에 따른 인식률의 변화를 조사하였으며, 이 결과 표준패턴의 수 15개, 학습회수 10회 이하, 샘플 수 3000 개일 경우가 가장 좋은 인식률을 보였다. 이 결과를 참고로 음소군별 인식실험 결과 모음 69.11%, 파열음 74.69%, 마찰음 및 파찰음 86.31%비음 및 유음 74.51%의 평균 인식률을 얻었다. 또한 , 한국어 49음소 전음소에 대한 인식실험 결과 71.2%의 인식률 얻어 MLVQ2의 유효성을 확인하였다.

• Journal of Biomedical Engineering Research
• /
• v.20 no.6
• /
• pp.591-599
• /
• 1999

연구개에 결함이 있는 사람의 발음은 부적절한 비음이 섞이게 되어 과비음성 비음이 되어 연구개를 복원해주는 시술을 하게 되는데, 과비음성 비음을 정량적으로 측정할 수있다면 시술 결과를 객관화 할 수 있게 된다. 현재 임상적으로 사용되고 있는 방법들은 관혈적이거나 고가의 장비를 필요로 한다. 본 논문에서는 비음의 특징인 스펙트럼에서 zero 의 존재와 비강에 의한 포만트의 존재 사실, 그리고 선형 예측 모델을 이용하여 마이크로폰과 사운드 카드가 장착된 PC로 구현할 수 있는 새로운 과비음성 비음 추정 알고리즘을 제안하였다. 음성 신호의 스펙트럼에 zero가 존재하는 경우, 낮은 차수(order)의 선형 예측 모델이 그 음성을 발음한 성도 시스템에 정확히 적용되지 않는다는 점을 이용하여, 같은 음성에 대한 높은 차수의 선형 예측 모델과의 차이를 이용해서 과비음성의 정량화를 시도했다. 본 논문에서는 제안된 알고리즘은 기존의 Teager Operator를 이용한 알고리즘에 비해서 Nasonmeter 의 측정결과와 더 높은 통계적 상관관계를 보여주었다.

• Journal of agricultural medicine and community health
• /
• v.37 no.1
• /
• pp.23-35
• /
• 2012

Objectives: The purpose of this study was to investigate the association of the average volume of alcohol consumption and binge drinking with arterial stiffness. Methods: The study population consisted of 5944 community-dwelling healthy adults aged 50 years and older. Average volume of alcohol consumption was calculated and frequency of binge drinking defined as the consumption of 7 or more drinks for men and 5 or more for women on a single occasion, was assessed using a structured interview. High brachial-ankle pulse wave velocity (baPWV), a marker of arterial stiffness, was defined as the highest gender-specific quartile of maximal baPWV distribution in the study population. Results: Compared to never drinkers, the multivariate-adjusted odds ratio (OR) of men who consumed 0.1-10.0, 10.1-20.0, 20.1-40.0, and >40.0 g/day was 0.93, 1.18, 1.38, and 2.36, respectively. The OR was 0.90, 0.97, 1.45, and 1.82 in women consuming 0.1-5.0, 5.1-10.0, 10.1-20.0, and >20.0 g/day, respectively. Binge drinking of <1 day/week (OR=1.66, 95% confidence interval [CI]=1.13-2.42) and ${\geq}1$ day/week (OR=1.61, 95% CI=1.04-2.50) were associated with increased risk for high baPWV in men, and binge drinking of ${\geq}1$ day/week (OR=3.12, 95% CI=1.16-8.34) was associated with increased risk for high baPWV in women. Conclusions: A J-shaped relationship between the average volume of alcohol consumption and high baPWV was observed, suggesting the detrimental effects of heavy alcohol drinking on arterial stiffness. Binge drinking was also significant risk factors for increased arterial stiffness, independently of the average volume of alcohol consumption.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.3
• /
• pp.2002-2011
• /
• 2015

This study was performed to determine the levels of physical function (ADL, IADL) and to reveal its association with the related factors in the elderly people. The study subjects were 1,756 (male 872, female 884) people aged over 70 who received medical check-ups and long-term care services between 2009 and 2012 from the National Health Insurance Corporation. As a result, the distribution of impaired ADL and IADL increased significantly with age. Logistic regression showed that the risk ratio of impaired ADL was increased significantly in the following groups: female, urban, low weight, stroke history group, smoking, alcohol drinking, and not regular exercise group. The risk ratio of an impaired IADL were increased significantly in the group of females, low weight, smoking, alcohol drinking. On the other hand the risk ratio of an impaired ADL and IADL was similar in each age group. As above results, the levels of ADL and IADL in the study subjects are closely related to the socio-demographic characteristics and health related behaviors. In particular, they suggested that the levels of ADL and IADL were lower in the poor group of the health-related behaviors, such as smoking, alcohol drinking, and regular exercise.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.105-115
• /
• 2018

The purpose of this study was to clarify whether or not alcohol drinking patterns are associated with sleep quality. A cross-sectional study was carried out by self-administered questionnaire in May, 2017 among 553 male workers who employed in manufacturing industries in D city. Logistic regression analysis was used to evaluate whether or not alcohol drinking patterns (as measured by frequency, amount of alcohol per day, and amount of alcohol per week) were associated with poor sleep quality (as measured by Pittsburgh Sleep Quality Index). As a result, in comparison with male workers who did not drink, the adjusted odds ratio for poor sleep quality was 0.44 (95% CI=0.232-0.845) for those who drank alcohol once a week or more, 0.31 (95% CI=0.192-0.829) for those who drank less than 1 glass daily, and 0.28 (95% CI=0.167-0.762) for those who drank 1-3 glasses daily. The results of this study suggest that some alcohol drinking patterns may affect sleep quality among male workers.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.5
• /
• pp.213-221
• /
• 2006

Phone segmentation of speech waveform is especially important for concatenative text to speech synthesis which uses segmented corpora for the construction of synthetic units. because the quality of synthesized speech depends critically on the accuracy of the segmentation. In the beginning. the phone segmentation was manually performed. but it brings the huge effort and the large time delay. HMM-based approaches adopted from automatic speech recognition are most widely used for automatic segmentation in speech synthesis, providing a consistent and accurate phone labeling scheme. Even the HMM-based approach has been successful, it may locate a phone boundary at a different position than expected. In this paper. we categorized adjacent phoneme pairs and analyzed the mismatches between hand-labeled transcriptions and HMM-based labels. Then we described the dominant error patterns that must be improved for the speech synthesis. For the experiment. hand labeled standard Korean speech DB from ETRI was used as a reference DB. Time difference larger than 20ms between hand-labeled phoneme boundary and auto-aligned boundary is treated as an automatic segmentation error. Our experimental results from female speaker revealed that plosive-vowel, affricate-vowel and vowel-liquid pairs showed high accuracies, 99%, 99.5% and 99% respectively. But stop-nasal, stop-liquid and nasal-liquid pairs showed very low accuracies, 45%, 50% and 55%. And these from male speaker revealed similar tendency.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.120-125
• /
• 1989

음성 신호에는 언어정보이외에 여러 요인에 의한 정보가 포함되어 있어서, 문자와 일대일로 대응되는 분절을 정확하게 검출하기가 어렵다. 본 연구에서는 선형 예측계수 (LPC) 스펙트럼의 첨두 부분을 강조한 이진 (binary) 스펙트럼을 제안하고, 이를 바탕으로 음의 안정영역과 천이영역을 통합하여 음향특징을 추출하고자 한다. 각 영역의 특징은 이진 스펙트럼을 누적하여 구하며, 통합적인 특징은 각 영역의 특징을 결합한 관계적 특징으로 나타낸다. 제 2 차 포르만트 주파수의 궤적을 관계적 특징으로 하여, 양순 비음과 치조 비음을 구별한 결과, 모음의 문맥과 화자에 비교적 독립적인 인식결과를 얻을 수 있었다. 또한 이진 스펙트럼이 원래의 스펙트럼에 포함된 정보를 유지하는지 검토하기 위해, 같은 거리척도 (distance measure) 에 의해 인식 실험한 결과 이진 스펙트럼의 성능이 오히려 우수하게 나타났으며, 관계적 이진 스펙트럼의 경우 화자에 따른 변화가 더욱 적었다. 음성에 백색 잡음 (Gaussian white noise)을 더하여 잡음음성 (noisy speech) 을 만든 뒤, 같은 방법으로 실험한 결과도 유사한 인식결과를 얻을 수 있어 제안된 이진 스펙트럼의 유효성을 확인하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.32-39
• /
• 1994

As a basic research to realize Korean speech recognition system, phoneme recognition was carried out to find out ; 1) the best place which represents each phoneme's characteristics, and 2) the reasonable length of duration for obtaining the best recognition rates. For the recognition experiments, multi-speaker dependent recognition with Bayesian decision rule using 21 order of cepstral coefficient as a feature parameter was adopted. It turned out that the best place of feature extraction for the highest recognition rates were 10~50ms in vowels, 40~100ms in fricatives and affricates, 10~50ms in nasals and liquids, and 10~50ms in plosives. And about 70ms of duration was good enough for the recognition of all 35 phonemes.

• Proceedings of the Korean Association for Survey Research Conference
• /
• 2001.04a
• /
• pp.59-71
• /
• 2001

We investigate design-based variance estimation methods of homogeneous linear estimator for population total under stratified multi-stage sampling. One method is unbiasedly estimating the first stage variance and the second stage variance separately in each stratum. And another is sub-sampling method that estimating the first stage variance only by using sub-sample selected from the second stage sample so that resulting estimator is unbiased for the total variance. The first is useful when the second stage unbiased estimator is available and the second is when the second stage variance is not estimable. For each case, we proposed a form of non-negative unbiased variance estimator. We expect the proposed variance estimation methods can be effectively used for many practical surveys.