• ETRI Journal
• /
• v.30 no.6
• /
• pp.865-867
• /
• 2008

A conventional environment adaptation for robust speech recognition is usually conducted using transform-based techniques. Here, we present a discriminative adaptation strategy based on a multi-condition-trained model, and propose a new method to provide universal application to a new environment using the environment's specific conditions. Experimental results show that a speech recognition system adapted using the proposed method works successfully for other conditions as well as for those of the new environment.

• Journal of information and communication convergence engineering
• /
• v.21 no.2
• /
• pp.139-144
• /
• 2023

Engineers prefer deep neural networks (DNNs) for solving computer vision problems. However, DNNs pose two major problems. First, neural networks require large amounts of well-labeled data for training. Second, the covariate shift problem is common in computer vision problems. Domain adaptation has been proposed to mitigate this problem. Recent work on adversarial-learning-based unsupervised domain adaptation (UDA) has explained transferability and enabled the model to learn robust features. Despite this advantage, current methods do not guarantee the distinguishability of the latent space unless they consider class-aware information of the target domain. Furthermore, source and target examples alone cannot efficiently extract domain-invariant features from the encoded spaces. To alleviate the problems of existing UDA methods, we propose the mixup regularization in adversarial discriminative domain adaptation (ADDA) method. We validated the effectiveness and generality of the proposed method by performing experiments under three adaptation scenarios: MNIST to USPS, SVHN to MNIST, and MNIST to MNIST-M.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.2
• /
• pp.83-89
• /
• 2000

In this paper, we proposed a discriminative adaptation method for PMC algorithm and achieved improved speech recognition rate. For the adaptation, we adopted modified PMC(MPMC) which is a variant of PMC and discriminatively adapted the association factor for each mixture of the HMM in the MPMC. From the recognition experiments, the proposed method showed better recognition rate than the conventional PMC. Also, compared with STAR algorithm which is another model parameter compensation method, the proposed method showed superior performance when the SNR is very low and the adaptation data is not sufficient.

• MALSORI
• /
• no.54
• /
• pp.73-83
• /
• 2005

The goal of our research is to build a text-independent speaker identification system that can be used in any condition without any additional adaptation process. The performance of speaker recognition systems can be severely degraded in some unknown mismatched microphone and noise conditions. In this paper, we show that PCA(principal component analysis) can improve the performance in the situation. We also propose an augmented PCA process, which augments class discriminative information to the original feature vectors before PCA transformation and selects the best direction for each pair of highly confusable speakers. The proposed method reduced the relative recognition error by 21%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.17-18
• /
• 2023

비지도형 도메인 적응(UDA)에 대한 최근 연구는 도메인 적응에 대한 설명 및 전이 가능한 특징을 풀어 내기 위해 적대적 학습에 의존한다. 그러나 기존 방법에는 대상 도메인의 클래스 인식(class-aware) 정보를 고려하지 않고는 잠재 공간의 구별 가능성을 완전히 보장할 수 없다는 것과 소스 및 대상 도메인의 샘플만으로는 잠재 공간에서 도메인 불변(domain- invariant) 특성을 추출하기에 부족하다는 두 가지 문제가 있다고 알려져 있다. 본 논문에서는 기존 알려진 UDA의 도메인 적응시 발생되는 문제를 해결하기 위해 Adversarial Discriminative Domain Adaptation(ADDA)에서 mixup을 활용해 신경망의 로버스트네스를 향상시키는 것을 확인하였다.

• Korean Journal of Acupuncture
• /
• v.24 no.2
• /
• pp.99-112
• /
• 2007

Objectives : It was to translate three neck and spinal pain disability questionnaires - the Neck Disability Index (NDI), the Neck Pain and Disability Scale (NPDS), and the Functional Rating Index (FRI) - into Korean language, and evaluate the psychometric properties of Korean versions of questionnaires to achieve a good cross-cultural adaptation. Methods : Forty (23 males, 17 females) subjects aged from 15 to 64 years old, participated to examine test-retest reliability. One hundred and eighty (76 males, 104 females) subjects with a primary diagnosis of non-specific neck pain and 81 healthy volunteers were undertaken to examine internal consistemcy, discriminative validity and longitudinal construct validity. Versions of each questionnaire in idiomatic modern Korean were developed using a procedure proposed by Beaton et al. (2000). To assess reliability, the Intraclass Correlation Coefficient (ICC $_{(2,1)}$) was calculated. Internal consistency was evaluated by Cronbach's alpha. Discriminative validity was examined with independent-group t-tests. Responsiveness was tested by calculating the effect size and standardized response mean for each questionnaire and using Pearson' s r and the area under the receiver operating characteristic curve analysis. Results : Test-retest reliability ofthe translated versions of the three disability questionnaires was excellent (ICC $_{(2,1)$ = 0.86-0.90). High internal consistency was found in the three disability questionnaires (Cronbach's alpha ranged from ${\alpha}=0.88$ for the FRI to ${\alpha}=0.96$ for the NPDS and 0.82 for the Short Form McGill Pain Questionnaire(SFMPQ)). the VAS subscale of the SFMPQ was found to be the most responsive of the subscales (ES=1.44, SRM=1.37). The VAS was also the most responsive pain and disability index in internal responsiveness analysis, although disability indices showed marginally better responsiveness when compared with external standards. No floor or ceiling effects were observed. Conclusions : It is concluded that the questionnaires were successfully translated and exhibit acceptable measurement properties, and may suggest that they are suitable for use in clinical and research application.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• Journal of Agricultural Extension & Community Development
• /
• v.18 no.1
• /
• pp.35-72
• /
• 2011

Study on children from international marriage so far has been conducted focusing on the school-aged children, and it uniformly presents those children as a mere being with problem, overlooking regional variables of rural area. Hence, this study aims to seek various means of adaptation of children from international marriage by considering both variables rural area and adolescence. For this study, six children from international marriage living in the rural area of H county in Jeonlanamdo were chosen, in-dept interview were conducted, and Giorgi(1985) was used to analyze qualitative data. The results shows that these adolescences appear to have extensive experiences in the areas of learning, personal relationship, home and identity. Level of academic achievement was influenced by what school they attend to, and personal relationship aspect was affected by prejudice and discriminative perception from people around them. In addition, in home environment, hatred toward father, sympathy for mother, comparison with mothers who have great cultural adaptation skills, and pressure as the firstborn appear to be on the increase. Adolescent children tend to be addicted to internet games in order to escape from anxiety, experiencing identity crisis. They tend to be negative about international marriage of their parents, and exhibit behaviors refusing values and religious view of their parents. At the conclusion, limitation of the study and suggestion for further study are presented.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.397-398
• /
• 2007

본 논문에서는 환경변화에 대해 강인하게 동작하는 음성인식 시스템을 위해 잡음적응 훈련과 변별학습 방식을 결합한 형태의 환경적응 방식을 제안한다. 다중환경 훈련과 잡음제거방식을 결합한 형태인 잡음적응 훈련 방식은 음성인식을 위한 MCE (Minimum Classification Error)의 목적과는 거리가 있고, 음성인식 시스템이 사용되는 모든 환경을 반영하는 것은 현실적으로 어렵다는 점에서 한계가 있다. 이에 잡음적응 훈련방식으로 훈련된 기본 음향모델을 목적환경에서 수집한 소량의 데이터를 이용한 변별학습을 통해 환경적응 모델로 변환함으로써 이러한 단점을 보완할 수 있는 잡음 적응 변별학습을 이용한 훈련방식을 제안한다.

• Journal of Fisheries and Marine Sciences Education
• /
• v.28 no.3
• /
• pp.661-666
• /
• 2016

This study was to explore the living experiences of the disabled adults who were participating in public education Yahak program held at evening class. The study designed in-depth interviews with ten disabled people using a grounded theory approach. Through analyzing process, 34 concepts, 15 subcategories, and eight categories were deduced. In axial coding, casual condition, 'Suffering from unknown cause disabilities' and 'Isolated by social cause', context condition, 'Taking discriminative treat for disabilities' impacted on phenomenon, 'Overcoming their conditions by themselves'. Intervening conditions was 'Taking social supports' and action-interaction condition, 'Enjoying public programs' totally lead to consequence in 'Controlling daily life' and 'Exploring their own social roles'. The periods of process were divided three stages, reflecting disabled situation, formation phase of social relation, and self-developing phase. The core category, 'Trying to be recognized as a member of society' incorporated the relationship between and among all categories and explained the process. The study indicates that social education program for the disabled helped to develop themselves as a member of society. Therefore, we suggest there may be a need for training for professionals who work with disabled people to develop social adaptation.