• 한국음향학회지
• /
• 제22권5호
• /
• pp.403-407
• /
• 2003

최근 고속화자적응 기법으로 eigenvoice 방식이 많이 사용되고 있다. Eigenvoice 적응방식에서도 적응화자의 적응 데이터가 매우 적은 경우에는 적절한 가중치의 추정이 어렵기 때문에 적응 데이터가 어느 정도 많은 경우에 비해 인식성능 향상이 크지 않다. 본 논문에서는 적응 데이터가 적을 때의 성능향상을 위하여 eigenvoice의 가중치 분포 특성을 이용한 eigenvoice 기반 고속화자적응을 제안한다. PBW 452 데이터베이스를 사용한 어휘독립 단어인식 실험 결과에서 가중치 문턱치(threshold) 적용 방식을 사용하여 적응 데이터가 매우 적은 경우의 상대적인 성능 저조 문제를 완화시켰다. 적응단어를 단 1개만 사용한 경우 가중치 문턱치 적용 방식을 사용하여 단어 오인식률을 9-18% 정도 감소시켰다.

• ETRI Journal
• /
• 제34권5호
• /
• pp.783-786
• /
• 2012

This letter proposes a more advanced joint maximum a posteriori (MAP) adaptation using a prior model based on a probabilistic scheme utilizing the bilinear transformation (BIT) concept. The proposed method not only has scalable parameters but is also based on a single prior distribution without the heuristic parameters of the previous joint BIT-MAP method. Experiment results, irrespective of the amount of adaptation data, show that the proposed method leads to a consistent improvement over the previous method.

• 대한음성학회지:말소리
• /
• 제68권
• /
• pp.33-47
• /
• 2008

In this paper, we propose a hybrid acoustic and pronunciation model adaptation method based on context dependency for Korean-English speech recognition. The proposed method is performed as follows. First, in order to derive pronunciation variant rules, an n-best phoneme sequence is obtained by phone recognition. Second, we decompose each rule into a context independent (CI) or a context dependent (CD) one. To this end, it is assumed that a different phoneme structure between Korean and English makes CI pronunciation variabilities while coarticulation effects are related to CD pronunciation variabilities. Finally, we perform an acoustic model adaptation and a pronunciation model adaptation for CI and CD pronunciation variabilities, respectively. It is shown from the Korean-English speech recognition experiments that the average word error rate (WER) is decreased by 36.0% when compared to the baseline that does not include any adaptation. In addition, the proposed method has a lower average WER than either the acoustic model adaptation or the pronunciation model adaptation.

• 대한가정학회지
• /
• 제37권10호
• /
• pp.107-122
• /
• 1999

Based on the theoretical framework of the Double ABCX model of family stress and adaptation, this study was to analysis the causal relationships of stressors (psychological sexual, and physical wife abuse), personal resources (self-efficacy and self-esteem) and social support(emotional and informational support), appraisal(positive appraisal and downward comparisons) with adaptation (psychological well-being and somatic symptoms). Self-administered questionnaire method was used to collect data from 264 wives residing in Chonbuk-do and Kyonggi-do area. The causal model was tested and modified by the maximum likelihood method using UISREL 7 program. Results showed that wife abuse had effect on adaptation indirectly through the latent variables of personal resource and appraisal, which influenced the adaptation directly. In addition, social support indirectly affect the adaptation through personal resource and appraisal. It was also found that all these variables explained 27.6% of the total variance of wives'adaptation, and that personal resources was the most powerful variable in predicting the adaptation of the wives.

• ETRI Journal
• /
• 제41권1호
• /
• pp.109-116
• /
• 2019

This paper explores new techniques that are based on a hidden-layer linear transformation for fast speaker adaptation used in deep neural networks (DNNs). Conventional methods using affine transformations are ineffective because they require a relatively large number of parameters to perform. Meanwhile, methods that employ singular-value decomposition (SVD) are utilized because they are effective at reducing adaptive parameters. However, a matrix decomposition is computationally expensive when using online services. We propose the use of an extended diagonal linear transformation method to minimize adaptation parameters without SVD to increase the performance level for tasks that require smaller degrees of adaptation. In Korean large vocabulary continuous speech recognition (LVCSR) tasks, the proposed method shows significant improvements with error-reduction rates of 8.4% and 17.1% in five and 50 conversational sentence adaptations, respectively. Compared with the adaptation methods using SVD, there is an increased recognition performance with fewer parameters.

• 전기전자학회논문지
• /
• 제24권4호
• /
• pp.998-1003
• /
• 2020

본 논문에서는 기존 감정 인식 시스템의 성능 향상을 위하여 감정 적응을 사용한 감정 학습 방법이 제안되었다. 감정 적응을 위하여 적은 개수의 학습 감정 음성과 감정 적응 방식을 사용하여 감정이 없는 음성 모델로부터 감정 음성 모델이 생성되었다. 이러한 방법은 기존 방법보다 적은 개수의 감정 음성을 사용하여도 우수한 성능을 나타내었다. 학습을 위하여 충분한 감정 음성을 얻는 것은 쉽지 않기 때문에 적은 개수의 감정 음성을 사용하는 것은 실제 상황에서 매우 실용적이다. 4가지 감정이 포함된 한국어 데이터베이스를 사용한 실험 결과에서 감정 적응을 이용한 제안된 방법이 기존 방법보다 우수한 성능을 나타내었다.

• 한국치위생학회지
• /
• 제11권5호
• /
• pp.811-822
• /
• 2011

Objectives : The purpose of this study was to examine the relationship of the self-efficacy of dental hygiene students to their stressors and ways of stress-adaptation patterns. Methods : The subjects in this study were dental hygiene juniors in four selected colleges located in the metropolitan area. Results : 1. They got a mean of 3.22 in self-efficacy. They gave the highest mark(3.50) to an item 'I can attain it if I set a primary goal.' 2. They got a mean of 3.18 in stressors. Among the stressors, task assignments(3.74) were identified as the greatest stressor, followed by the curriculum(3.25), learning environments(3.16), prospects of employment (3.07) and test anxiety(2.95). 3. They got a mean of 2.02 in stress-adaptation method. They got 2.31 and 1.72 in long-term and short-term adaptation respectively, which showed that long-term stress adaptation method were more prevailing than short-term ones. 4. As a result of analyzing whether there would be any gaps in self-efficacy according to general characteristics, statistically significant gaps were found in that regard according to experience of preparing for college admission after leaving high school, academic standing, satisfaction with the department of dental hygiene and prospects of employment(p<.05). 5. As a result of checking the relationship of their self-efficacy to their stressors and ways of stress adaptation method, there were statistically significant differences in that aspect according to examinations and prospect of employment(p<0.05). As for ways of stress adaptation method, there were statistically significant differences in long-term adaptation method (p<0.05). Conclusions : As it's found that the level of the self-efficacy of the dental hygiene students was linked to the efficiency of their ways of stress adaptation method, the development and implementation of programs geared toward boosting the self-efficacy of dental hygiene students are required to teach them to successfully cope with various kinds of stress that they are likely to face after getting a job.

• ETRI Journal
• /
• 제29권6호
• /
• pp.794-807
• /
• 2007

In the mobile Internet, users generally work with handheld devices with limited computing power and small screens. Their access conditions also change frequently. In this paper, we present a novel method supporting intelligent content adaptation to better suit handheld devices. The underpinning is a unit of information (UOI)-based content adaptation method, which automatically detects semantic relationships among the components of Web contents and then reorganizes page layout to fit handheld devices based on identified UOIs. Experimental results demonstrate that our method enables more sensitive content adaptation.

• 전기학회논문지
• /
• 제66권7호
• /
• pp.1105-1110
• /
• 2017

Speech with various emotions degrades the performance of the speaker recognition system. In this paper, a speaker recognition method using emotional adaptation has been proposed to improve the performance of speaker recognition system using affective speech. For emotional adaptation, emotional speaker model was generated from speaker model without emotion using a small number of training affective speech and speaker adaptation method. Since it is not easy to obtain a sufficient affective speech for training from a speaker, it is very practical to use a small number of affective speeches in a real situation. The proposed method was evaluated using a Korean database containing four emotions. Experimental results show that the proposed method has better performance than conventional methods in speaker verification and speaker recognition.

• ETRI Journal
• /
• 제24권6호
• /
• pp.469-472
• /
• 2002

Speaker adaptation techniques are generally used to reduce speaker differences in speech recognition. In this work, we focus on the features fitted to a linear regression-based speaker adaptation. These are obtained by feature transformation based on independent component analysis (ICA), and the feature transformation matrices are estimated from the training data and adaptation data. Since the adaptation data is not sufficient to reliably estimate the ICA-based feature transformation matrix, it is necessary to adjust the ICA-based feature transformation matrix estimated from a new speaker utterance. To cope with this problem, we propose a smoothing method through a linear interpolation between the speaker-independent (SI) feature transformation matrix and the speaker-dependent (SD) feature transformation matrix. From our experiments, we observed that the proposed method is more effective in the mismatched case. In the mismatched case, the adaptation performance is improved because the smoothed feature transformation matrix makes speaker adaptation using noisy speech more robust.