• The Journal of the Acoustical Society of Korea
• /
• v.32 no.5
• /
• pp.423-429
• /
• 2013

The present study aimed to find the most sensitive placement of the skull to perceive speech through the bone vibrator in various protection methods while being exposed to noise. Twenty young normal-hearing adults (10 male and 10 female) participated in the study. As stimulus, Korean spondee words were presented via one of five skull locations (i.e., jaw angle, condyle, temple, mastoid, and vertex), while the participants wore one of four protection methods (i.e., ear form, ear plug, ear muff, and ear form and muff together) against white noise in one of four noise directions (i.e., 0, 90, 180, 270 degrees). The results showed: 1) there was a significant difference among the five skull locations with condyle being the most sensitive placement; 2) there was a significant difference among the four protection methods, with the ear form plus ear muff condition (or dual protection) providing the lowest threshold; 3) when exposed to noise from 90 degrees, the significantly lowest threshold was found; 4) there was no significant difference in results by gender. The pattern of results suggests that the communicative condition via the condyle bone conduction and the dual protection of the air conduction under any noise direction might be ideal for preventing noise-induced hearing loss, although further studies should be undertaken in this area.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.28 no.3
• /
• pp.251-262
• /
• 2014

This article is for understanding dementia with the perspective of Korean Medicine through research on syndrome differentiations of dementia clinically applied and relations between modern diseases and Korean Medicine pattern types of dementia. clinical papers were searched in China Academic Journals(CAJ) of China National Knowledge Infrastructure(CNKI) from 2012 to 2013. Conclusions are as follows. First, dementia was expressed in many ways such as imbecility, stupidity, fatuity, idiocy, vacuity, etc and was related with amnesia, forgetfulness, speech not in the right order, depressive psychosis(quiet insanity), manic psychosis, depression syndrome. Second, prescriptions such as QiFuYin and ZuoGuiWan from JingYueQuanShu, XiXinTang and ZhiMiTang from BianZhengLu, TongQiaoHuoXueTang, XueFuZhuYuTang and BuYangHaiWuTang from YiLinGaiCuo, HaiShaoDan from YiFangJiJie, HuangLianJieDuTang from WaiTaiMiYao were suggested for dementia. Third, syndrome differentiation pattern types of dementia are kidney deficiency and marrow decrease, qi-blood depletion, liver-kidney depletion, spleen-kidney depletion, heart-spleen deficiency as deficiency patterns and effulgent heart-liver fire, ascendant hyperactivity of liver yang, qi stagnation and blood stasis, phlegm turbidity obstructing orifice, phlegm-blood stasis obstructing orifice, intense heat toxin as excess patterns and qi deficiency with blood stasis, yin deficiency with yang hyperactivity as deficiency-excess complex patterns. Major pattern types are kidney deficiency and marrow decrease, phlegm-blood stasis obstructing orifice, qi stagnation and blood stasis, liver-kidney depletion, phlegm turbidity obstructing orifice.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.2E
• /
• pp.41-50
• /
• 1994

This paper proposes a DMS(Dynamic Multi-Section) model based on the information of the similar features in word pattern. This model represents each word as a time series of several sections and each section implies duration time information and typical feature vectors. The procedure to make a model in the word pattern is that typical feature vector and duration time information are reflected in the distance, when matching between word pattern and model is repeated. As the result of it, the accumulated distance by matching is to be minimized.

• Journal of KIISE:Software and Applications
• /
• v.37 no.12
• /
• pp.946-950
• /
• 2010

Many sentiment categorization systems based on machine learning methods use morphological analyzers in order to extract linguistic features from sentences. However, the morphological analyzers do not generally perform well in a customer review domain because online customer reviews include many spacing errors and spelling errors. These low performances of the underlying systems lead to performance decreases of the sentiment categorization systems. To resolve this problem, we propose a feature extraction method based on simple longest matching of Eojeol (a Korean spacing unit) and phoneme patterns. The two kinds of patterns are automatically constructed from a large amount of POS (part-of-speech) tagged corpus. Eojeol patterns consist of Eojeols including content words such as nouns and verbs. Phoneme patterns consist of leading consonant and vowel pairs of predicate words such as verbs and adjectives because spelling errors seldom occur in leading consonants and vowels. To evaluate the proposed method, we implemented a sentiment categorization system using a SVM (Support Vector Machine) as a machine learner. In the experiment with Korean customer reviews, the sentiment categorization system using the proposed method outperformed that using a morphological analyzer as a feature extractor.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.3
• /
• pp.40-52
• /
• 1992

In this paper, we propose the speaker adaptive word recognition method using a mapped membership function, in order to absorb a fluctuation owing to personal difference which is a problem of speaker independent speech recognition. In the training procedure of this method, the mapped membership function is made with the fuzzy theory introducded into a mapped codebook, between an unknown speaker's spectrum pattern and a standard speaker's one. In the recognition procedure, an input pattern of an unknown speaker is reconstructed to the pattern which is adapted to that of a standard speaker by the mapped membership function. To show the validity of this method, word recognition experiments are carried out using 28 DDD area names. The recognition rate of the conventional speaker-adaptive method using a mapped codebook by VQ is 64.9[%], and that made by a fuzzy VQ is 76.2[%]. Throughout the experiment using a mapped membership function, we can achieve 95.4[%] recognition rate. This shows that our proposed method is more excellent in recognition performance. Moreover, this method doesn't need an iterative training procedure to make the mapped membership function, and memory capacity and computation requirements for this method are reduced to 1/30 and 1/500 time of those for the conventional method using a mapped codebook, respectively.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.97-100
• /
• 1999

본 논문은 자동차의 편의성 및 안전성의 동시 확보를 위하여, 보조적 스위치의 조작없이 상시 음성의 입$\cdot$출력이 가능하도록 하였고, 남성과 여성을 구별하기 위하여 피치검출법을 사용하여 속도별로 구분하였다. 또한, band pass filter를 이용하여 자동으로 잡음하에서 정확하게 음성추간 검출(End Point Detection)을 하게 하였다. Reference Pattern은 DMS(Dynaminc Multi-Section)[1]모델을 사용하려고, 음성의 특징 파라미터와 인식 알고리즘은 PLP 13차와 One Stage Dynamic Programming(OSDP)를 사용하였다. 시내주행중인 자동차 환경에서 자주 사용되는 차량제어 명령어 30단어를 가지고 실험한 결과 40-80km에서 화자독립 남성 $96\%$, 여성 $94.4\%$ 화자종속일 때 남성 $97\%$, 여성 $95\%$의 인식률을 얻을수 있었고 남성과 여성을 구분하므로 써 인식률을 향상 시켰다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.337-340
• /
• 1999

The most salient and discussed features of speech production in agrammatic aphasia are the omission and substitution of grammatical morphemes. Cross-linguistic studies have shown that the pattern of omission/substitution is not random but occurs in a systematic and highly constrained way. Although these descriptions are important, they do not explain why all grammatical morphemes are not equally impaired. Friedmann and Grodzinsky (1997) proposed the Tree-Pruning Hypothesis (TPH) to account for these patterns of sparing and loss. The TPH claims that in an agrammatic representation, an impaired functional node is underspecified, thus allowing inappropriate affixation to occur. Additionally, whenever a node is impaired, all nodes above it will also be impaired. Using four types of narratives collected from two Korean agrammatic patients, We test the claim that the impairment in agrammatism is based on such hierarchical representation. It was found that these patients consistently produced appropriate grammatical morphemes that are higher in a syntactic tree than the impaired morphemes. The finding that an intact node exists higher than an impaired node refutes the TPH.

• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.64-69
• /
• 2002

This study concerns the constraints of English Poetic Meter. In English poems, the metrical pattern doesn't always match the linguistic stress on the lines. These mismatches are found differently among the poets. For the lexical stress mismatched with the weak metrical position, $*W{\Rightarrow}{\;}Strength$ is established by the concept of the strong syllable. The peaks of monosyllabic words mismatched with the weak metrical position are divided according to which side of the boundary of a phonological domain they are adjacent to. Adjacency Constraint I is suggested for the mismatched peak which is adjacent to the left boundary of a phonological domain; *Peak] and Adjacency ConstraintII for the mismatched peak which are adjacent to the right boundary of a phonological domain. These constraints are various according to the poets(Pope, Milton and Shakespeare) : *[Peak [-stress], $W{\Rightarrow}{\;}*Strength$ and *Peak] in Pope; *[+stress][Peak [-stress] and *Peak] in Milton ; *[+stress][Peak [-stress], $W{\;}{\Rightarrow}{\;}*Strength$ and ACII in Shakespeare.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.20 no.42
• /
• pp.161-169
• /
• 1997

A variety of learning methods are used for neural networks. Among them, the backpropagation algorithm is most widely used in such image processing, speech recognition, and pattern recognition. Despite its popularity for these application, its main problem is associated with the running time, namely, too much time is spent for the learning. This paper suggests a method which maximize the convergence speed of the learning. Such reduction in e learning time of the backpropagation algorithm is possible through an adaptive adjusting of the slope of the activation function depending on total errors, which is named as the variable slope algorithm. Moreover experimental results using this variable slope algorithm is compared against conventional backpropagation algorithm and other variations; which shows an improvement in the performance over pervious algorithms.

• Korean Journal of Child Studies
• /
• v.27 no.2
• /
• pp.1-14
• /
• 2006

This study examined the spontaneous utterances of 20 1-2 year old Korean-Chinese children in Yanji, China by videotaping their spontaneous natural speech during interaction with his/her caregiver for 30 minutes on 4 separate occasions. Utterances were transcribed and coded by nominative and accusative case markers; then analyzed by grammatical functions. Results showed that the order and pattern of the acquisition of the case marking system of Korean-Chinese bilinguals differed from that of Korean monolinguals. Bilinguals used the accusative marker -lul earlier than the nominative marker-ka and overextended the accusative marker more often than the nominative marker. These results are consistent with those of Gathercole (in press) who found that bilingual children differed from monolinguals in mastering grammar.