• 한국정보통신학회논문지
• /
• 제16권2호
• /
• pp.237-245
• /
• 2012

본 논문은 암묵신호분리방법을 이용하여 동시통화를 가능하게 하는 음향반향제거기에 관한 것이다. 음향반향 제거기는 동시통화 구간에서 성능이 저하되거나 발산하게 된다. 그래서 근단화자신호를 추정해서 잔차신호로부터 차감하기 위하여 암묵신호분리방법을 사용한다. 암묵신호분리방법은 이중 마이크를 가지고 2차 통계적 성질을 이용한 반복적인 계산에 의해 근단화자신호를 추정해낸다. 그런데 폐쇄된 반향환경에서 암묵신호분리의 혼합모델은 다채널이기 때문에 분리계수를 직접 계산하지 않고 반향제거기의 계수를 복사하여 그대로 사용한다. 많은 시뮬레이션을 통하여 제안한 음향반향제거기의 성능을 검증하였다. 시뮬레이션 결과, 이 방법을 사용한 음향반향제거기는 동시통화의 유무에 상관없이 안전하게 동작하고, 일반적인 LMS 알고리즘에 비해 ERLE가 평균 20dB 향상되는 것으로 나타났다.

• 대한임베디드공학회논문지
• /
• 제8권4호
• /
• pp.185-194
• /
• 2013

Abstract- In distant-talking environments, speech recognition performance degrades significantly due to noise and reverberation. Recent work of Michael L. Selzer shows that in microphone array speech recognition, the word error rate can be significantly reduced by adapting the beamformer weights to generate a sequence of features which maximizes the likelihood of the correct hypothesis. In this approach, called Likelihood Maximizing Beamforming algorithm (Limabeam), one of the method to implement this Limabeam is an UnSupervised Limabeam(USL) that can improve recognition performance in any situation of environment. From our investigation for this USL, we could see that because the performance of optimization depends strongly on the transcription output of the first recognition step, the output become unstable and this may lead lower performance. In order to improve recognition performance of USL, some post-filter techniques can be employed to obtain more correct transcription output of the first step. In this work, as a post-filtering technique for first recognition step of USL, we propose to add a Wiener-Filter combined with Feature Weighted Malahanobis Distance to improve recognition performance. We also suggest an alternative way to implement Limabeam algorithm for Hidden Markov Network (HM-Net) speech recognizer for efficient implementation. Speech recognition experiments performed in real distant-talking environment confirm the efficacy of Limabeam algorithm in HM-Net speech recognition system and also confirm the improved performance by the proposed method.

• 한국산학기술학회논문지
• /
• 제13권5호
• /
• pp.2305-2312
• /
• 2012

시대의 변화에 따른 IT 기술의 급속한 발전은 전반적인 산업영역에서 예전보다 쉽게 정보를 취득하고 가공할 수 있는 여건을 형성하고 있다. 최근 각광 받고 있는 SNS의 변화를 살펴보면 스마트폰 이용이 대중화되면서 마케팅 툴로서의 가치가 더욱 급부상하고 있다. 본 연구는 패션 마케팅 분야에서 새로운 시장으로 떠오르고 있는 Facebook 활용 사례를 연구하였다. 패션업체 10곳을 선정하여 활동지표의 기준이 되는 '게시글', 'like this', 'people talking about this' '이벤트'를 중심으로 페이스북 페이지를 연구하였고 spearman 순위 상관계수를 이용하여 위 지표들 간의 상관분석을 실시하였다. 연구 결과 '게시글'과 'like this'의 관계는 높은 상관관계를 보여 주었고 다른 요인들 사이에서는 상관관계를 확인할 수 없었다. 페이스북 페이지를 이용한 마케팅은 소비자와 업체와의 소통이 기존 매체에 비해 원활하였는데 이는 SNS의 마케팅의 이용이 기존의 마케팅의 한계였던 소통의 벽을 넘을 수 있음을 보여주는 결과였다.

• 한국가정과학회지
• /
• 제7권2호
• /
• pp.47-58
• /
• 2004

This study is designed to provide some basic materials for finding better ways to promote student-parent communication in order to elevate the sense of self-esteem among middle school students and to talk about the importance of communication between students and parents through looking at the current student-parent communication reality resulting from socio-demographic changes among male and female middle school students and analyzing some influences student-parent communication has on students' self-esteem. To attain the aforementioned purpose, total 650 2nd grade and 3rd grade middle school students were asked to fill out the questionnaire. The schools that they are attending are 2 schools in Gwangju City and 2 schools in a township in Jeonnam. 617 students responded to the survey. In order to see the general characteristics and the distribution of major variables of the respondents, the data were used to produce frequency. percentile, standard deviation and correlation quotient. and t-test. one-way Anova, Duncan's multiple range test and multiple regression analysis techniques were put to use. The results from this study are as follows: student groups that have good relations with other students seemed to be more open and active in their communication with their mother and father. Female students and students in their 2nd grade had more open talking relations with their mothers than male students and students in their 3rd grade. Students had more open talking relations with their father when father's occupation is office worker. In the difference of self-esteem that results from variables in communication between students and parents, a significant variance was presented in the level of the self-esteem of middle school students. When they had open communication with both parents, they had a high sense of self-esteem. and when their communication style was problematic, they had a low sense of self-esteem. When they had better relations with other students, when they had more open communication styles with their mother, when they had better school records, when they felt more satisfaction with communication With their father, they showed a higher level of self-esteem.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.303-304
• /
• 2007

In this paper, we implement an automatic distance speech recognition system for voiced-enabled services. We first construct a baseline automatic speech recognition (ASR) system, where acoustic models are trained from speech utterances spoken by using a cross-talking microphone. In order to improve the performance of the baseline ASR using distance speech, the acoustic models are adapted to adjust the spectral characteristics of speech according to different microphones and the environmental mismatches between cross-talking and distance speech. Next we develop a voice activity detection algorithm for distance speech. We compare the performance of the base-line system and the developed ASR system on a task of PBW (Phonetically Balanced Word) 452. As a result it is shown that the developed ASR system provides the average word error rate (WER) reduction of 30.6 % compared to the baseline ASR system.

• 영미문화
• /
• 제10권2호
• /
• pp.1-27
• /
• 2010

By taking the form of a fictional autobiography, a Japanese American woman writer Lydia Minatoya tries to solve the inexpressible confliction which Japanese Americans experience in their living in America. In her first published fiction, Talking to High Monks in the Snow, the writer faithfully tries to follow the Japanese I-story tradition where meandering of personal petit histories and frequent self-pities are constructed without solid action, characters and plot. Here appear many accidental others whom function as significant yet fleeting subalterns. In contrast, in the second fiction, The Strangeness of Beauty published seven years later, the I-narratives undergoes some drastic transformations by authorial intrusion, dramatic and haiku styles, and appearances of actorial agents. Just working as an invisible yet important stagehand (kuroko in Japanese) behind the stage of life, the author now handles her own self-inquiry through more controllable distance and maturity as directors or photographers often do. However, despite achieving dramatic actions and artistic elegance mainly thanks to her adoption of western masterpieces's grand narratives, Minatoya seems to stop in the midway in her tallying work of fiction with fact by delaying the larger imaginable conflict through which the temporarily gained autonomy can be turned into a disaster anytime. Nonetheless, the reader feels relieved and encouraged after recognizing the fragile Asian female self's transformation as a new, flexible and autonomous self by her unwavering contact with two contrasting cultures and providing silent minority female characters with gradually stronger and uncannier voices.

• 한국음향학회지
• /
• 제29권2호
• /
• pp.125-132
• /
• 2010

예로부터 사람의 말을 흉내 낼 수 있는 동물들은 특별한 대우를 받고 있다. 이러한 동물은 앵무새를 비롯한 매우 극소수에 해당하며, 닭이 사람의 목소리를 내는 경우는 지금까지 알려진 바가 없다. 본 논문에서는 최근 화제가 된 한국과 키르기스스탄의 말하는 닭의 발성 특성을 살펴보고, 발음 통계와 실제 음원을 분석하였다. 분석결과 닭이 실제로 사람과 대화를 하는 것은 아니지만, 닭의 날개를 잡을 경우 "안돼," "아니야" 등의 한글 발음을 하는 것으로 확인하였으며, 키르기스스탄의 닭 역시 사람과 매우 유사한 발음을 하는 것으로 확인되었다. 청음 설문조사 결과에서도 대부분의 사람이 닭이 말하는 단어를 인지하였으며, 닭이 내는 소리로 판단한사람은 없었다. 이처럼 닭이 사람의 발음을 할수 있는 이유는, 선천적인 발음기관과 발성시의 기질적 특정이 일반 닭과 현저히 다르며, 사람에게 붙잡힐 때 긴장에 따른 성대/발성 특성 변화때문으로 판단된다.

• Molecules and Cells
• /
• 제26권2호
• /
• pp.107-112
• /
• 2008

Invasion mechanisms of pathogens and counteracting defense mechanisms of plants are highly diverse and perpetually evolving. While most classical studies of plant defense have focused only on defense-specific factor-mediated responses, recent work is beginning to shed light on the involvement of non-stress signal components, especially growth and developmental processes. This shift in focus links plant resistance more closely with growth and development. In this review, we summarize our current understanding of how pathogens manipulate host developmental processes and, conversely, of how plants deploy their developmental processes for self-protection. We conclude by introducing our recent work on UNI, a novel R protein in Arabidopsis which mediates cross-talk between developmental processes and defense responses.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.2775-2781
• /
• 2011

Urban Transit Train Radio is Radio Communication system that is used official business as leading motive for train safety running among the train crew and the central control center and drive-caring-chamber on main line and branch line. This system is operated that organizes talking path on handset of terminal after the train crew receives audio and understands call voice on speaker of terminal at calling the train of the central control center. When the central control center calls the specific train uses all call radio form, the train crew doesn't recognize the call cause the train situation, noise and action as train control. So there is a delay response cause reset call at the central control center. This research discusses the management of subway radio system and describes the call the train system that recognize train call number of all-call used between the central control center and the train crew.

• 아동학회지
• /
• 제29권1호
• /
• pp.115-131
• /
• 2008

Using the narrative method of qualitative research, this study of the puerperal period (6 weeks just after delivery) analyzed how mothers, after birthing their first child, changed from women to mothers. The survey of 8 mothers was implemented by personal interviews, talking on the phone, or chatting on the internet 5 to 7 times each over one year. Results showed that mothers first realized that they were changing from women to mothers by experiencing sudden physical changes through delivery and lactation and by such childrearing behaviors as feeding, bathing, and putting their child to bed. Mothers recognized this process was facilitated by relationships with others owing to their shared interest in the child.