• ETRI Journal
• /
• v.33 no.1
• /
• pp.99-109
• /
• 2011

This paper concerns a robust real-time voice activity detection (VAD) approach which is easy to understand and implement. The proposed approach employs several short-term speech/nonspeech discriminating features in a voting paradigm to achieve a reliable performance in different environments. This paper mainly focuses on the performance improvement of a recently proposed approach which uses spectral peak valley difference (SPVD) as a feature for silence detection. The main issue of this paper is to apply a set of features with SPVD to improve the VAD robustness. The proposed approach uses a weighted voting scheme in order to take the discriminative power of the employed feature set into account. The experiments show that the proposed approach is more robust than the baseline approach from different points of view, including channel distortion and threshold selection. The proposed approach is also compared with some other VAD techniques for better confirmation of its achievements. Using the proposed weighted voting approach, the average VAD performance is increased to 89.29% for 5 different noise types and 8 SNR levels. The resulting performance is 13.79% higher than the approach based only on SPVD and even 2.25% higher than the not-weighted voting scheme.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.21 no.7
• /
• pp.900-910
• /
• 1997

Multiblock structured grids are, to a large extent, capable of filling up topologically complex flow domains in an efficient way. The proposed approach enables to use different flow models in each different block and the easy incorporation of different grid refinement strategies for different blocks. Furthermore, it may be expected that this multiblock structured approach will naturally lead to the parallel executions of calculations per block on different vector processors. In this paper, the hypercube + + structure is proposed for topological informations on multiblock grids and the B-spline volume for geometrical informations. Three samples of the-three dimensional results are presented to demonstrate the capabilities of the present approach.

• International Journal of Advanced Culture Technology
• /
• v.12 no.2
• /
• pp.180-189
• /
• 2024

We aimed to see if approach-avoidance visual experience would have different effects in the valence rating of emojis. Previous literature has shown that approach-avoidance tendencies have influences people's emotional perceptions. Up until now, research on emojis have been heavily focused on static emojis, which gives room for exploration whether if movement added on to emoji would elicit different emotional responses. In the study, we examined the impact of approach-avoidance visual experience of emojis via mobile interface, categorized into 4 experimental conditions (positive approach, negative approach, positive avoid, and negative avoid), and conducted semi-structured interviews to identify users' reasonings towards their valence ratings on specific emojis with approach or avoid movements. We found that positive approach emojis were the highest valence rating and preferred by the participants, while there were no differences between negative emoji approach or avoidance. Based on these findings, we conclude that positive emojis could be intensified to be more positive with approach motion, yet for negative emojis, individual differences or contextual differences may arise in its emotional ratings.

• Archives of Plastic Surgery
• /
• v.35 no.2
• /
• pp.152-158
• /
• 2008

Purpose: Mandibulotomy approach and mandible sparing approach are most common methods for oropharyngeal cancer surgery. Good surgical view and convenience of flap inset are advantages of mandibulotomy approach but deformity of mandible contour, postoperative malocclusion and radionecrosis are its limitations. To make up for the limitations, mandible sparing method is commonly performed, but limited surgical view and difficulties of flap inset are the weak points of this approach. The purpose of the study is to compare mandibulotomy and mandible sparing approaches in postoperative complications and progression of the treatment in oropharyngeal cancer operation and reconstruction. Methods: Single reconstructive microsurgeon operated for oropharyngeal cancer patients with different surgeons of head and neck department who prefer mandibulotomy and mandible sparing approach respectively, and we compared the frequency of postoperative complication, operation time, duration of hospitalization and recurrence rate between two different surgical approaches. Results: Mandibulotomy approach was used in 18 patients and mandible sparing approach was used in 15 patients. In mandibulotomy approach, there happened one case of teeth injury and one case of necrosis of skin and gingiva, but there happened no malocclusion and radionecrosis. In mandible sparing approach, there were 3 cases of fistula and 2 cases of infection which are significantly higher than mandibulotomy approach. There were no significant differences between early regional recurrence and duration of hospitalization. Conclusion: In this study we compared two different methods for the surgical approach in oropharyngeal cancer surgery. As mandible sparing approach has difficulties of limited surgical view, it can be used for the limited indications of anterior tongue and mouth floor cancer. Mandibulotomy approach has advantages of good surgical view and convenience of flap inset. In this method preservation of gingival tissue, watertight fashion suture, delicate osteotomy and plate fixation to maintain occlusion are the key points for the successful results.

• Journal of information and communication convergence engineering
• /
• v.17 no.2
• /
• pp.117-127
• /
• 2019

In software engineering, to ensure reliability between systems, describing both system architecture and assurance arguments between system elements is considered necessary. There are proposals for system architecture assurance, but use of these traditional methods often requires development of different diagrams using different editors. Because the visual sense of the traditional methods is inadequate, errors readily occur when manipulating different diagrams. Therefore, it is essential that the assurance of dependability between components and systems is visualized and easy to understand. In this paper, an integrated approach to describe the relationship between system actors and system architecture is proposed, and this approach is clarified using an enterprise architecture modeling language. A case study is carried out and comparison to the traditional approach $d^*$ framework is explained. The comparison results show that the proposed approach is more suitable for ensuring dependability in system architecture.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.23-25
• /
• 2021

This paper describes an approach of composing music with multiple AI composers. This approach enriches more the creativity space of artificial intelligence music composition than using only one composer. This paper presents a simple example with 2 different deep learning composers working together for composing one music. For the experiment, the two composers adopt the same deep learning architecture of an LSTM model trained with different data. The output of a composer is a sequence of notes. Each composer alternatively appends its output to the resulting music which is input to both the composers. Experiments compare different music generated by the proposed multiple composer approach with the traditional one composer approach.

• The Korean Journal of Applied Statistics
• /
• v.23 no.6
• /
• pp.1245-1253
• /
• 2010

There are two main approaches for estimating the discontinuous regression function nonparametrically. One is the direct approach, the other is the indirect approach. The major goal of the two approaches are different. The direct approach focuses on the overall good estimation of the regression function itself, whereas the indirect approach focuses on the good estimation of jump locations. Apparently, the two approaches are quite different in nature. Gijbels et al. (2007) argue that the comparison of two approaches does not make much sense and that it is even difficult to choose an appropriate criterion for comparisons. However, it is obvious that the indirect approach also has the regression curve estimate as the subsidiary result. Therefore it is necessary to verify the appropriateness of the indirect approach as the estimator of the discontinuous regression function itself. Park (2009a) compared the performance of two approaches through a simulation study. In this paper, we consider a more general case and draw some useful conclusions.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.957-963
• /
• 2004

A new agreement measure for multivariate interval data by different sets of raters is proposed. The proposed approach builds on Um's multivariate extension of Cohen's kappa. The proposed measure is compared with corresponding earlier measures based on Berry and Mielke's approach and Janson and Olsson approach, respectively. Application of the proposed measure is exemplified using hypothetical data set.

• Journal of Information Processing Systems
• /
• v.13 no.2
• /
• pp.400-416
• /
• 2017

Music emotion is an important component in the field of music information retrieval and computational musicology. This paper proposes an approach for automatic emotion classification, based on rough set (RS) theory. In the proposed approach, four different sets of music features are extracted, representing dynamics, rhythm, spectral, and harmony. From the features, five different statistical parameters are considered as attributes, including up to the $4^{th}$ order central moments of each feature, and covariance components of mutual ones. The large number of attributes is controlled by RS-based approach, in which superfluous features are removed, to obtain indispensable ones. In addition, RS-based approach makes it possible to visualize which attributes play a significant role in the generated rules, and also determine the strength of each rule for classification. The experiments have been performed to find out which audio features and which of the different statistical parameters derived from them are important for emotion classification. Also, the resulting indispensable attributes and the usefulness of covariance components have been discussed. The overall classification accuracy with all statistical parameters has recorded comparatively better than currently existing methods on a pair of datasets.

• ETRI Journal
• /
• v.33 no.6
• /
• pp.914-923
• /
• 2011

This paper concerns robust and reliable speaker model training for text-independent speaker verification. The baseline speaker modeling approach is the Gaussian mixture model (GMM). In text-independent speaker verification, the amount of speech data may be different for speakers. However, we still wish the modeling approach to perform equally well for all speakers. Besides, the modeling technique must be least vulnerable against unseen data. A traditional approach for GMM training is expectation maximization (EM) method, which is known for its overfitting problem and its weakness in handling insufficient training data. To tackle these problems, variational approximation is proposed. Variational approaches are known to be robust against overtraining and data insufficiency. We evaluated the proposed approach on two different databases, namely KING and TFarsdat. The experiments show that the proposed approach improves the performance on TFarsdat and KING databases by 0.56% and 4.81%, respectively. Also, the experiments show that the variationally optimized GMM is more robust against noise and the verification error rate in noisy environments for TFarsdat dataset decreases by 1.52%.