• 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.

• MALSORI
• /
• no.56
• /
• pp.207-223
• /
• 2005

The goal of language model adaptation is to improve the background language model with a relatively small adaptation corpus. This study presents a language model adaptation technique where additional text data for the adaptation do not exist. We propose the information retrieval (IR) technique with N-gram language modeling to collect the adaptation corpus from baseline text data. We also propose to use a dynamic language model interpolation coefficient to combine the background language model and the adapted language model. The interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech data reserved for held-out validation data. This allows the final adapted model to improve the performance of the background model consistently The proposed approach reduces the word error rate by $13.6\%$ relative to baseline 4-gram for two-hour broadcast news speech recognition.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.188-193
• /
• 2003

Regardless of the distribution of the adaptation data in the testing environment, model-based adaptation methods that have so far been reported in various literature incorporates the adaptation data undiscriminatingly in reducing the mismatch between the training and testing environments. When the amount of data is small and the parameter tying is extensive, adaptation based on outlier data can be detrimental to the performance of the recognizer. The distribution of the adaptation data plays a critical role on the adaptation performance. In order to maximally improve the recognition rate in the testing environment using only a small number of adaptation data, supervised weighted training is applied to the structural maximum a posterior (SMAP) algorithm. We evaluate the performance of the proposed weighted SMAP (WSMAP) and SMAP on TIDIGITS corpus. The proposed WSMAP has been found to perform better for a small amount of data. The general idea of incorporating the distribution of the adaptation data is applicable to other adaptation algorithms.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.403-407
• /
• 2003

Recently, eigenvoice approach has been widely used for rapid speaker adaptation. However, even in the eigenvoice approach, Performance improvement using very small amount of adaptation data is relatively small in comparison with that using somewhat large adaptation data because the reliable estimation of weights of eigenvoice is difficult. In this paper, we propose a rapid speaker adaptation method based on eigenvoice using the weight distribution characteristics to improve the performance on a small adaptation data. In the Experimental results on vocabulary-independent word recognition task (using PBW 452 database), the weight threshold method alleviates the problem of relatively low performance for a tiny small adaptation data. When single adaptation word is used, word error rate is reduced about 9-18% by the weight threshold method.

• 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 ...

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1994.04a
• /
• pp.627-632
• /
• 1994

This study suggests the contingency framework understanding the implementation of NIMT and conducts empirical analysis using survey data. The main objectives of the thesis are as follows : (1) analyzing the relationship between adaptation requirements and organizational adaptation efforts. (2) analyzing the relationship between organizational adaptation efforts and implementation performance, and the moderating effect of the adaptation requirements. (3) analyzing the relationship between organizational adaptation efforts and organization characteristics(organization size, technical capability, top management support). A field study was undertaken to test the hypothesized relationships among adaptation efforts, adaptations requirements, organization characteristics, implementation performance. Data were collected from 52 NMT implementation projects of 45 machine tool, metal component firms. The emprical relflts indicated that adaptation requirrnents, organization characteristics were significantly related to organizational adaptation efforts and adaptation efforts can significantly improve implementation perfomance, but the moderating effect of adaptation requirements on adaptation efforts and implementation performance was not supported.

• Journal of Communications and Networks
• /
• v.9 no.3
• /
• pp.213-218
• /
• 2007

Methods for symbol-by-symbol channel feedback and adaptation of symbol durations have been recently proposed. In this paper, we quantitatively analyze the gain in error-constrained data throughput due to such an extremely rapid adaptation of symbol durations to fast-time-varying channels. The results show that a symbol-by-symbol adaptation can achieve a throughput gain by orders of magnitude over a frame-by-frame adaptation.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.383-383
• /
• 2000

In this paper, a motion adaptation control is applied for animation of 3-D human character. The method includes parameterization of joint motion data, motion adaptation based on body ratio of character, dynamic adaptation using genetic algorithm, etc. The feasibility of motion adaptation technique is verified by applying to motion control and adaptation of a 3-D human character.

• Journal of Korean Academy of Nursing
• /
• v.45 no.4
• /
• pp.501-512
• /
• 2015

Purpose: The purpose of this study, which was guided by the Resiliency Model of Family Stress, Adjustment, and Adaptation, was twofold: (a) to explore family and parental adaptation and factors influencing family adaptation in Korean families of children with Down syndrome (DS) through a quantitative methodology and (b) to understand the life with a Korean child with DS through a qualitative method. Methods: A mixed-methods design was adopted. A total of 147 parents of children with DS completed a package of questionnaires, and 19 parents participated in the in-depth interviews. Quantitative and qualitative data were analyzed using stepwise multiple regression and content analysis respectively. Results: According to the quantitative data, the overall family adaptation scores indicated average family functioning. Financial status was an important variable in understanding both family and parental adaptation. Family adaptation was best explained by family problem solving and coping communication, condition management ability, and family hardiness. Family strains and family hardiness were the family factors with the most influence on parental adaption. Qualitative data analysis showed that family life with a child with DS encompassed both positive and negative aspects and was expressed with 5 themes, 10 categories, and 16 sub-categories. Conclusion: Results of this study expand our limited knowledge and understanding concerning families of children with DS in Korea and can be used to develop effective interventions to improve the adaptation of family as a unit as well as parental adaptation.

• Journal of Korean Academy of Nursing Administration
• /
• v.19 no.4
• /
• pp.536-543
• /
• 2013

Purpose: The purpose of this study was to identify the mediating effect of professionalism in the relationship between clinical competence and field adaptation in newly graduated nurses. Methods: The participants in this study were 213 nurses from four tertiary hospitals who had less than 12 months of nursing experience. Data were collected during January and February, 2013. A structured questionnaire was used for data collection and data were analyzed using descriptive statistics, Pearson correlation coefficients, and path analysis with the SPSS/WIN 21.0 and AMOS 21.0 programs. Results: The mean score for clinical competence was $2.85{\pm}0.25$, for professionalism, $3.10{\pm}0.30$, and for field adaptation, $2.79{\pm}0.37$. There was a significant positive relationship between clinical competence and field adaptation. Also, professionalism was positively correlated with field adaptation. Professionalism showed mediating effects between clinical competence and field adaptation. Improvement of clinical competence increased professionalism and the increased professionalism raised the field adaptation. Conclusion: Based on these findings, orientation programs including strategies to increase professionalism, should be established to promote effective field adaptation in newly graduated nurses. These orientation programs can strengthen professionalism, the mediator between clinical competence and field adaptation in newly graduated nurses.