• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.95-101
• /
• 2017

This paper proposes a new method to train Deep Neural Network (DNN)-based acoustic models for speech recognition of native and foreign speakers. The proposed method consists of determining multi-set state clusters with various acoustic properties, training a DNN-based acoustic model, and recognizing speech based on the model. In the proposed method, hidden nodes of DNN are shared, but output nodes are separated to accommodate different acoustic properties for native and foreign speech. In an English speech recognition task for speakers of Korean and English respectively, the proposed method is shown to slightly improve recognition accuracy compared to the conventional multi-condition training method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.3
• /
• pp.487-499
• /
• 2022

Machine learning such as deep learning have been widely used in recent years. Recently deep learning is performed in a trusted execution environment such as ARM TrustZone to improve security in edge devices and embedded devices with low computing resource. To mitigate this problem, we propose TPMP that efficiently uses the limited memory of TEE through DNN model partitioning. TPMP achieves high confidentiality of DNN by performing DNN models that could not be run with existing memory scheduling methods in TEE through optimized memory scheduling. TPMP required a similar amount of computational resources to previous methodologies.

• The Journal of the Korea Contents Association
• /
• v.20 no.10
• /
• pp.715-725
• /
• 2020

In this paper, we propose an optimization scheme for a k-Nearest Neighbor(k-NN) query, which finds k objects closest to the query in the high dimensional feature vectors. The k-NN query is converted and processed into a range query based on the range that is likely to contain k data. In this paper, we propose an optimization scheme using DNN model to derive an optimal range that can reduce processing cost and accelerate search speed. The entire system of the proposed scheme is composed of online and offline modules. In the online module, a query is actually processed when it is issued from a client. In the offline module, an optimal range is derived for the query by using the DNN model and is delivered to the online module. It is shown through various performance evaluations that the proposed scheme outperforms the existing schemes.

• Transactions of Materials Processing
• /
• v.29 no.2
• /
• pp.89-96
• /
• 2020

The finite element method has been widely applied in the sheet metal forming process. However, the finite element method is computationally expensive and time consuming. In order to tackle this problem, surrogate modeling methods have been proposed. An artificial neural network (ANN) is one such surrogate model and has been well studied over the past decades. However, when it comes to ANN with two or more layers, so called deep neural networks (DNN), there is distinct a lack of research. We chose to use DNNs our surrogate model to predict the behavior of sheet metal in the deep drawing process. Thickness variation is selected as an output of the DNN in order to evaluate workpiece feasibility. Input variables of the DNN are radius of die, die corner and blank holder force. Finite element analysis was conducted to obtain data for surrogate model construction and testing. Sampling points were determined by full factorial, latin hyper cube and monte carlo methods. We investigated the performance of the DNN according to its structure, number of nodes and number of layers, then it was compared with a radial basis function surrogate model using various sampling methods and numbers. The results show that our DNN could be used as an efficient surrogate model for the deep drawing process.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.47-50
• /
• 2019

This paper proposes an acoustic model adaptation method for effective speech recognition in noisy environments. In the proposed algorithm, the noise corruption function is estimated employing DNN (Deep Neural Network), and the function is applied to the model parameter estimation. The experimental results using the Aurora 2.0 framework and database demonstrate that the proposed model adaptation method shows more effective in known and unknown noisy environments compared to the conventional methods. In particular, the experiments of the unknown environments show 15.87 % of relative improvement in the average of WER (Word Error Rate).

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.187-196
• /
• 2024

In this study, we propose a DNN (Deep Neural Network)-based sign language translation model that can significantly reduce training time by compressing sign language coordinates. We compared and analyzed the accuracy and training time of the model with and without sign language coordinate compression. The results of using the proposed model for sign language translation showed that while the accuracy decreased by approximately 5.9% after compressing the sign language video, the training time was reduced by 56.57%, indicating a substantial gain in training efficiency compared to the loss in translation accuracy.

• Journal of Advanced Navigation Technology
• /
• v.24 no.5
• /
• pp.430-437
• /
• 2020

The proposed model implements a model that improves the face prediction rate and recognition rate through learning with an artificial neural network using face detection, landmark and face recognition algorithms. After landmarking in the face images of a specific person, the proposed model use the previously learned Caffe model to extract face detection and embedding vector 128D. The learning is learned by building machine learning algorithms such as support vector machine (SVM) and deep neural network (DNN). Face recognition is tested with a face image different from the learned figure using the learned model. As a result of the experiment, the result of learning with DNN rather than SVM showed better prediction rate and recognition rate. However, when the hidden layer of DNN is increased, the prediction rate increases but the recognition rate decreases. This is judged as overfitting caused by a small number of objects to be recognized. As a result of learning by adding a clear face image to the proposed model, it is confirmed that the result of high prediction rate and recognition rate can be obtained. This research will be able to obtain better recognition and prediction rates through effective deep learning establishment by utilizing more face image data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.3
• /
• pp.571-578
• /
• 2018

Recently, deep learning techniques have shown superior performance in various kinds of pattern recognition. However, there have been some arguments whether the DNN performs better than the conventional machine learning techniques when classification experiments are done using a small amount of training data. In this study, we compared the performance of the conventional GMM and SVM with DNN, a kind of deep learning techniques, in audio event detection. When tested on the same data, DNN has shown superior overall performance but SVM was better than DNN in segment-based F-score.

• Journal of Internet of Things and Convergence
• /
• v.8 no.3
• /
• pp.55-61
• /
• 2022

In order to reduce greenhouse gases, the main culprit of global warming, the United Nations signed the Climate Change Convention in 1992. Korea is also pursuing a policy to expand the supply of renewable energy to reduce greenhouse gas emissions. The expansion of renewable energy development using solar power led to the expansion of wind power and solar power generation. The expansion of renewable energy development, which is greatly affected by weather conditions, is creating difficulties in managing the supply and demand of the power system. To solve this problem, the power brokerage market was introduced. Therefore, in order to participate in the power brokerage market, it is necessary to predict the amount of power generation. In this paper, the prediction system was used to analyze the Yonchuk solar power plant. As a result of applying solar insolation from on-site (Model 1) and the Korea Meteorological Administration (Model 2), it was confirmed that accuracy of Model 2 was 3% higher. As a result of comparative analysis of the DNN and RNN models, it was confirmed that the prediction accuracy of the DNN model improved by 1.72%.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.506-511
• /
• 2018

This paper proposes an GMM(Gaussian Mixture Model)-DNN(Deep Neural Network) hybrid-based feature compensation method for effective speech recognition in noisy environments. In the proposed algorithm, the posterior probability for the conventional GMM-based feature compensation method is calculated using DNN. The experimental results using the Aurora 2.0 framework and database demonstrate that the proposed GMM-DNN hybrid-based feature compensation method shows more effective in Known and Unknown noisy environments compared to the GMM-based method. In particular, the experiments of the Unknown environments show 9.13 % of relative improvement in the average of WER (Word Error Rate) and considerable improvements in lower SNR (Signal to Noise Ratio) conditions such as 0 and 5 dB SNR.