• Title/Summary/Keyword: model adaptation

Search Result 1,101, Processing Time 0.03 seconds

Development of a Structural Equation Model for Children's Adaptation in Divorced Families (회복력 요인 중심의 이혼가정 아동 적응모형)

  • Shin, Sung-Hee
    • Journal of Korean Academy of Nursing
    • /
    • v.40 no.1
    • /
    • pp.127-138
    • /
    • 2010
  • Purpose: This study was designed to develop and test a structural model for children's adaptation in divorced families. The hypothetical model was constructed based on the Family Resilience Model by McCubbin and McCubbin. Methods: Data were collected using self-report questionnaires from 219 children (3-6th grade) in divorced families. The children attended one of 22 community agencies, 8 after-school programs, 3 elementary schools in three cities in South Korea. The collected data were analyzed using LISREL program to test the hypothetical model. Results: The modified model was constructed by deleting four paths in accordance with the statistical and theoretical criteria. Compared to the hypothetical model, the revised one had a better fit to the data. Self-esteem, and beliefs about parental divorce had direct effects, and family communication and internal control had indirect effects on children's adaptation in divorced families. These variables explained 56% of the variance in children's adaptation. Conclusion: The modified model was supported by empirical data. This model could be applied to family nursing interventions with divorced families or any other suffering family transition. When working with children experiencing parental divorce, it is important for nurses to enhance children's self-esteem, family communication and to decrease children's negative beliefs about parental divorce to help in their adaptation.

A New Speaker Adaptation Technique using Maximum Model Distance

  • Lee, Man-Hyung;Hong, Suh-Il
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2001.10a
    • /
    • pp.99.1-99
    • /
    • 2001
  • This paper presented an adaptation approach based on maximum model distance (MMD) method. This method shares the same framework as they are used for training speech recognizers with abundant training data. The MMD method could adapt to all the models with or without adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 65.55% phoneme error reduction is achieved. The MMD could reduce phoneme error by 16.91% even when only one adaptation utterance is used.

  • PDF

SVM Based Speaker Verification Using Sparse Maximum A Posteriori Adaptation

  • Kim, Younggwan;Roh, Jaeyoung;Kim, Hoirin
    • IEIE Transactions on Smart Processing and Computing
    • /
    • v.2 no.5
    • /
    • pp.277-281
    • /
    • 2013
  • Modern speaker verification systems based on support vector machines (SVMs) use Gaussian mixture model (GMM) supervectors as their input feature vectors, and the maximum a posteriori (MAP) adaptation is a conventional method for generating speaker-dependent GMMs by adapting a universal background model (UBM). MAP adaptation requires the appropriate amount of input utterance due to the number of model parameters to be estimated. On the other hand, with limited utterances, unreliable MAP adaptation can be performed, which causes adaptation noise even though the Bayesian priors used in the MAP adaptation smooth the movements between the UBM and speaker dependent GMMs. This paper proposes a sparse MAP adaptation method, which is known to perform well in the automatic speech recognition area. By introducing sparse MAP adaptation to the GMM-SVM-based speaker verification system, the adaptation noise can be mitigated effectively. The proposed method utilizes the L0 norm as a regularizer to induce sparsity. The experimental results on the TIMIT database showed that the sparse MAP-based GMM-SVM speaker verification system yields a 42.6% relative reduction in the equal error rate with few additional computations.

  • PDF

A Prediction Model on Adaptation to University Life among Chinese International Students in Korea (중국 유학생의 한국 대학생활 적응 예측모형)

  • Lin, Qin Lan;Kim, Hee-Kyung
    • The Journal of Korean Academic Society of Nursing Education
    • /
    • v.17 no.3
    • /
    • pp.501-513
    • /
    • 2011
  • Purpose: On the basis of the theoretical framework of a combination of Roy's adaptation theory and Lazarus & Folkman's theory of stress - appraise coping, the purpose of this study was to predict effect factors of adaptation to university life of Chinese international students in Korea. After this, a model of adaptation to university life of Chinese international students in Korea was constructed. Methods: A questionnaire was used to survey 369 Chinese international students from one university in Korea, which was analyzed by using PASW Statistics 18.0 and LISREL 8.7. Results: This theoretical model explained adaptation to university life of Chinese international students at 75.0% in Korea. Physical symptoms, loneliness, acculturation stress and self-efficacy directly affected the adaptation to university life. Korean language proficiency indirectly affected adaptation to university life through self-efficacy. Conclusion: Results of this study provided theoretical basis for the future health care of university- centered health centers. For improving adaptation to university life of Chinese international students in Korea, education and nursing measures for reducing physical symptoms, loneliness and acculturation stress, and improving Korean language proficiency and self-efficacy are proposed for further research and development.

A New Speaker Adaptation Technique using Maximum Model Distance

  • Tahk, Min-Jea
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2001.10a
    • /
    • pp.154.2-154
    • /
    • 2001
  • This paper presented a adaptation approach based on maximum model distance (MMD) method. This method shares the same framework as they are used for training speech recognizers with abundant training data. The MMD method could adapt to all the models with or without adaptation data. If large amount of adaptation data is available, these methods could gradually approximate the speaker-dependent ones. The approach is evaluated through the phoneme recognition task on the TIMIT corpus. On the speaker adaptation experiments, up to 65.55% phoneme error reduction is achieved. The MMD could reduce phoneme error by 16.91% even when ...

  • PDF

The Effect of Parent's Support on School Adaptation of Immigrant Adolescents: Mediating Effect of Self-esteem and Moderating Effect of Cultural Adaptation Stress (부모의 지지가 중도입국 청소년의 학교생활 적응에 미치는 영향 : 자아존중감의 매개효과 및 문화적응 스트레스의 조절효과)

  • Davaadelger Erdenesuren;Hye-Jung Cho
    • Journal of Industrial Convergence
    • /
    • v.22 no.7
    • /
    • pp.103-112
    • /
    • 2024
  • The purpose of this study is to verify the effect of parent's support on the school adaptation of immigrant adolescents to school life, the mediating effect of self-esteem, and the moderating effect of cultural adaptation stress. The data used for the analysis were the second panel data (2020) among the multicultural youth panel survey data. As for the data analysis method, frequency analysis, descriptive statistics analysis, correlation analysis, PROCESS MACRO Model Number 4 and PROCESS MACRO Model Number 1 analysis were performed. As a result of the analysis, first, parental support showed a positive (+) effect on school life adaptation. Second, in the relationship between parent's support and school adaptation, self-esteem had a statistically significant indirect effect. Third, it was found that cultural adaptation stress had no moderating effect in the relationship between parent's support and school adaptation. Based on these results, policy and practical suggestions for improving the school adaptation of immigrant adolescents to school life were presented.

Feasibility of Application of Roy's Adaptation Model to Family Health Assessment (로이적응모델의 가족건강사정에의 적용가능성)

  • Jang Sun-Ok
    • Journal of Korean Public Health Nursing
    • /
    • v.8 no.2
    • /
    • pp.35-56
    • /
    • 1994
  • This article was intended to survey whether Roy' Adapation model ('Roy Model') can be applied to family health assessment and to study whether application of the Roy Model to a Korean family is feasible. under the Roy Model, a family is viewed as an adaptation system having a series of process of input. process, feedback, and output. Further, the Roy Model indicates that a family contains Physiolosical, self-concept. role function and interdependent mode in respect of internal or external stimuli. In the event where the family health assessed, the adaptation mode of that family must be assess at the first stage. Then, the focal, contextual, residual stimuli affecting the family must be assessed. In 1984 Hanson suggested four types of family adaptation mode based upon the Roy Model and thereby enhanced the possibility for family health assessment. In order survey whether the Roy Model can be applied to the Korean family, the author of this article contracted adults of 169 who live in 'A' city to make open questions regarding family and then analyzed responses from them by utilizing Roy model. This study categorized family Adaptation mode based upon the' four types of family adaptation mode developed by Hanson. As a result of this study, family adaptation mode was categorized into 117 concepts. Those 117 concepts are consisted or Physiolosical mode of 47. self­concept mode of 56, role function mode of 9 and interdependent mode of 5. Further. stimuli affecting family were classified based upon Roy's definition as to three types of stimuli. Stimuli on a family are comprised focal stimuli concept of 19, contextual stimuli concepts of 19, one residual stimuli concept. this result implies that the Roy's Model can be applied to Korean family. Physiological mode shows meaning of survival. while self-concept mode reflects meaning of growth and emphasizes harmony among the family based on the familism. The role function mode shows continuity rather control of family member. By contrast, interdependent mode shows interaction with community to which the family belongs. but the degree of interaction does not appear too high. The analysis of family stimuli led this study to conclude that troubles within a family. changes in family structure and diease of family member generate stimuli. However, an application of the Roy Model contains the following problems: First, Roy argued that the family adaptation mode should be assessed at the first level family health assessment and then stimuli affecting family adaptation should be adaptation assessed at the second stage. To the belief of the author of this article. however, for checking family adaptation level. focal, contextual, residual stimuli should be confirmed by assessing stimuli at first stage. Then, the family adaptation mode in respect of such stimuli should be assessed. The rationale for this is that the family adaptation level is determined depending on degree of strength of focal. contextual. residual stimuli. Second. Whall (1991) raised a question 'Does one assess family adaptation mode and intervene in the stimuli?' 'Likewise, assessment of the family adaptation should be made in the following manner in order for family health to be enhanced. Third. Roy believes that additional stimuli (such as contextual and residual) are same as internal process (including nurturance. support, and socialization). However, the basis for this Roy's belief is not too clear. In spite of these problems which the author indicated above, it can be concluded that the Roy Model can serve as a good device for an assessment of family health and that the Roy Model can be applied to a Korean family. Finally, further research of family adaptation theory and family nursing theory is required for a development of these theories.

  • PDF

Sequential Adaptation Algorithm Based on Transformation Space Model for Speech Recognition (음성인식을 위한 변환 공간 모델에 근거한 순차 적응기법)

  • Kim, Dong-Kook;Chang, Joo-Hyuk;Kim, Nam-Soo
    • Speech Sciences
    • /
    • v.11 no.4
    • /
    • pp.75-88
    • /
    • 2004
  • In this paper, we propose a new approach to sequential linear regression adaptation of continuous density hidden Markov models (CDHMMs) based on transformation space model (TSM). The proposed TSM which characterizes the a priori knowledge of the training speakers associated with maximum likelihood linear regression (MLLR) matrix parameters is effectively described in terms of the latent variable models. The TSM provides various sources of information such as the correlation information, the prior distribution, and the prior knowledge of the regression parameters that are very useful for rapid adaptation. The quasi-Bayes (QB) estimation algorithm is formulated to incrementally update the hyperparameters of the TSM and regression matrices simultaneously. Experimental results showed that the proposed TSM approach is better than that of the conventional quasi-Bayes linear regression (QBLR) algorithm for a small amount of adaptation data.

  • PDF

Families of Children with Disabilities: The Test of a Structural Model of Family Income, Hardiness, Pile-up Stress, Communication and Family Adaptation (장애아동 가족의 수입, 내구력, 누적 스트레스, 의사소통, 가족적응에 대한 구조모델검증)

  • 오승아
    • Journal of the Korean Home Economics Association
    • /
    • v.40 no.9
    • /
    • pp.175-189
    • /
    • 2002
  • The purpose of this study was to test a structural model about family income as causally related to family hardiness, pile-up stress, communication, and family adaptation in families of children with disabilities. 250 families of children with disabilities participated as subjects. The models were developed on the basis of confirmatory factor analysis and compared using covariance structure modeling(LISREL). Adequate fitness of the model was observed. Family income showed negative effect on pile-up stress and positive effect on family adaptation. Pile-up stress showed negative effect on family hardiness. Family hardiness showed positive effect on family communication, and family communication showed positive effect on family adaptation.

Performance Enhancement for Speaker Verification Using Incremental Robust Adaptation in GMM (가무시안 혼합모델에서 점진적 강인적응을 통한 화자확인 성능개선)

  • Kim, Eun-Young;Seo, Chang-Woo;Lim, Yong-Hwan;Jeon, Seong-Chae
    • The Journal of the Acoustical Society of Korea
    • /
    • v.28 no.3
    • /
    • pp.268-272
    • /
    • 2009
  • In this paper, we propose a Gaussian Mixture Model (GMM) based incremental robust adaptation with a forgetting factor for the speaker verification. Speaker recognition system uses a speaker model adaptation method with small amounts of data in order to obtain a good performance. However, a conventional adaptation method has vulnerable to the outlier from the irregular utterance variations and the presence noise, which results in inaccurate speaker model. As time goes by, a rate in which new data are adapted to a model is reduced. The proposed algorithm uses an incremental robust adaptation in order to reduce effect of outlier and use forgetting factor in order to maintain adaptive rate of new data on GMM based speaker model. The incremental robust adaptation uses a method which registers small amount of data in a speaker recognition model and adapts a model to new data to be tested. Experimental results from the data set gathered over seven months show that the proposed algorithm is robust against outliers and maintains adaptive rate of new data.