• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.640-645
• /
• 2021

The deep learning based end-to-end TTS system consists of Text2Mel module that generates spectrogram from text, and vocoder module that synthesizes speech signals from spectrogram. Recently, by applying deep learning technology to the TTS system the intelligibility and naturalness of the synthesized speech is as improved as human vocalization. However, it has the disadvantage that the inference speed for synthesizing speech is very slow compared to the conventional method. The inference speed can be improved by applying the non-autoregressive method which can generate speech samples in parallel independent of previously generated samples. In this paper, we introduce FastSpeech, FastSpeech 2, and FastPitch as Text2Mel technology, and Parallel WaveGAN, Multi-band MelGAN, and WaveGlow as vocoder technology applying non-autoregressive method. And we implement them to verify whether it can be processed in real time. Experimental results show that by the obtained RTF all the presented methods are sufficiently capable of real-time processing. And it can be seen that the size of the learned model is about tens to hundreds of megabytes except WaveGlow, and it can be applied to the embedded environment where the memory is limited.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.81-90
• /
• 2020

This paper describes a method of building Korean conversational speech data in the emergency medical domain and proposes an annotation method for the collected data in order to improve speech recognition performance. To suggest future research directions, baseline speech recognition experiments were conducted by using partial data that were collected and annotated. All voices were recorded at 16-bit resolution at 16 kHz sampling rate. A total of 166 conversations were collected, amounting to 8 hours and 35 minutes. Various information was manually transcribed such as orthography, pronunciation, dialect, noise, and medical information using Praat. Baseline speech recognition experiments were used to depict problems related to speech recognition in the emergency medical domain. The Korean conversational speech data presented in this paper are first-stage data in the emergency medical domain and are expected to be used as training data for developing conversational systems for emergency medical applications.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1579-1590
• /
• 2020

In this paper, spatially-adaptive denormalization (SPADE) based U-Net is proposed to detect changes by using high-resolution satellite images. The proposed network is to preserve spatial information using SPADE. Change detection methods using high-resolution satellite images can be used to resolve various urban problems such as city planning and forecasting. For using pixel-based change detection, which is a conventional method such as Iteratively Reweighted-Multivariate Alteration Detection (IR-MAD), unchanged areas will be detected as changing areas because changes in pixels are sensitive to the state of the environment such as seasonal changes between images. Therefore, in this paper, to precisely detect the changes of the objects that consist of the city in time-series satellite images, the semantic spatial objects that consist of the city are defined, extracted through deep learning based image segmentation, and then analyzed the changes between areas to carry out change detection. The semantic objects for analyzing changes were defined as six classes: building, road, farmland, vinyl house, forest area, and waterside area. Each network model learned with KOMPSAT-3A satellite images performs a change detection for the time-series KOMPSAT-3 satellite images. For objective assessments for change detection, we use F1-score, kappa. We found that the proposed method gives a better performance compared to U-Net and UNet++ by achieving an average F1-score of 0.77, kappa of 77.29.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.4
• /
• pp.125-132
• /
• 2021

As the layers of artificial neural network deepens, and the dimension of data used as an input increases, there is a problem of high arithmetic operation requiring a lot of arithmetic operation at a high speed in the learning and recognition of the neural network (NN). Thus, this study proposes a data dimensionality reduction method to reduce the dimension of the input data in the NN. The proposed Line-segment Feature Analysis (LFA) algorithm applies a gradient-based edge detection algorithm using median filters to analyze the line-segment features of the objects existing in an image. Concerning the extracted edge image, the eigenvalues corresponding to eight kinds of line-segment are calculated, using 3×3 or 5×5-sized detection filters consisting of the coefficient values, including [0, 1, 2, 4, 8, 16, 32, 64, and 128]. Two one-dimensional 256-sized data are produced, accumulating the same response values from the eigenvalue calculated with each detection filter, and the two data elements are added up. Two LFA256 data are merged to produce 512-sized LAF512 data. For the performance evaluation of the proposed LFA algorithm to reduce the data dimension for the recognition of handwritten numbers, as a result of a comparative experiment, using the PCA technique and AlexNet model, LFA256 and LFA512 showed a recognition performance respectively of 98.7% and 99%.

• Smart Media Journal
• /
• v.11 no.4
• /
• pp.46-55
• /
• 2022

It is very important to first detect and remove defective fruits with scratches or bruised areas in the automatic fruit quality screening system. This paper proposes a method of detecting defective areas in fruits using the latest artificial intelligence technology, the Yolo V4 deep learning model in order to overcome the limitations of the method of detecting fruit's defective areas using the existing image processing techniques. In this study, a total of 2,400 defective fruits, including 1,000 defective apples and 1,400 defective fruits with scratch or decayed areas, were learned using the Yolo V4 deep learning model and experiments were conducted to detect defective areas. As a result of the performance test, the precision of apples is 0.80, recall is 0.76, IoU is 69.92% and mAP is 65.27%. The precision of pears is 0.86, recall is 0.81, IoU is 70.54% and mAP is 68.75%. The method proposed in this study can dramatically improve the performance of the existing automatic fruit quality screening system by accurately selecting fruits with defective areas in real time rather than using the existing image processing techniques.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.45-51
• /
• 2021

With the development of deep learning, semantic segmentation methods are being studied in various fields. There is a problem that segmenation accuracy drops in fields that require accuracy such as medical image analysis. In this paper, we improved PSPNet, which is a deep learning based segmentation method to minimized the loss of features during semantic segmentation. Conventional deep learning based segmentation methods result in lower resolution and loss of object features during feature extraction and compression. Due to these losses, the edge and the internal information of the object are lost, and there is a problem that the accuracy at the time of object segmentation is lowered. To solve these problems, we improved PSPNet, which is a semantic segmentation model. The multi-scale attention proposed to the conventional PSPNet was added to prevent feature loss of objects. The feature purification process was performed by applying the attention method to the conventional PPM module. By suppressing unnecessary feature information, eadg and texture information was improved. The proposed method trained on the Cityscapes dataset and use the segmentation index MIoU for quantitative evaluation. As a result of the experiment, the segmentation accuracy was improved by about 1.5% compared to the conventional PSPNet.

• Journal of the Korean Society of Earth Science Education
• /
• v.15 no.1
• /
• pp.62-75
• /
• 2022

In this study, experiential STEAM program using 3D printer was produced focusing on the content elements of 'solar' in the 2015 revised science curriculum, and in order to find out the effectiveness of the STEAM program, analyzed creative problem solving, STEAM attitude, and STEAM satisfaction by applying it to two middle school 77 students simple random sampled. The results of this study are as follows. First, a solar tactile model was produced using a 3D printer, and a program was developed to enable students to actively learn experience-oriented activities through visual impairment experiences. Second, in the response sample t-test by the difference in pre- and post-score of STEAM attitude tests, significant statistical test results were shown in 'interest', 'consideration', 'self-concept', 'self-efficacy', and 'science and engineering career choice' sub-factors except 'consideration' and 'usefulness / value recognition' sub-factors (p<.05). Third,, the STEAM satisfaction test conducted after the application of the 3D printer-based STEAM program showed that the average value range of sub-factors were 3.66~3.97, which improved students' understanding and interest in science subjects through the 3D printer-based STEAM program.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.13-20
• /
• 2022

IEEE 802.11ay Wi-Fi is the next generation wireless technology and operates in mmWave band. It supports the MU-MIMO (Multiple User Multiple Input Multiple Output) transmission in which an AP (Access Point) can transmit multiple data streams simultaneously to multiple STAs (Stations). To this end, the AP should perform MU-MIMO beamforming training with the STAs. For efficient MU-MIMO beamforming training, it is important for the AP to estimate signal strength measured at each STA at which multiple beams are used simultaneously. Therefore, in the paper, we propose a deep learning-based link quality estimation scheme. Our proposed scheme estimates the signal strength with high accuracy by utilizing a deep learning model pre-trained for a certain indoor or outdoor propagation scenario. Specifically, to estimate the signal strength of the multiple concurrent beams, our scheme uses the signal strengths of the respective single beams, which can be obtained without additional signaling overhead, as the input of the deep learning model. For performance evaluation, we utilized a Q-D (Quasi-Deterministic) Channel Realization open source software and extensive channel measurement campaigns were conducted with NIST (National Institute of Standards and Technology) to implement the millimeter wave (mmWave) channel. Our simulation results demonstrate that our proposed scheme outperforms comparison schemes in terms of the accuracy of the signal strength estimation.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.4
• /
• pp.349-357
• /
• 2021

Recently, drones are rapidly becoming common and expanding. There is a great need for diversity in whether drone flight data can be used as entertainment technology analysis data. In particular, it is necessary to check whether it is possible to analyze and utilize the flight and operation process of entertainment drones, which are developing through autonomous and intelligent methods, through data analysis and machine learning. In this paper, it was confirmed whether it can be used as a machine learning technology by using FC data in the evaluation of drones for entertainment. As a result, FC data from DJI and Parrot such as Mavic2 and Anafi were unable to analyze machine learning for entertainment. It is because data is collected at intervals of 0.1 second or more, so that it is impossible to find correlation with other data with GCS. On the other hand, it was found that machine learning technologies can be applied in the case of Fixhawk, which used an ARM processor and operates with the Nuttx OS. In the future, it is necessary to develop technologies capable of analyzing the characteristics of entertainment by dividing fixed-wing and rotary-wing flight information. For this, a model shoud be developed, and systematic big data collection and research should be conducted.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.363-369
• /
• 2021

High-definition road maps are used as the basic infrastructure for autonomous vehicles, so the latest road information must be quickly reflected. However, the current drawing and structural editing process of high-definition road maps are manually performed. In addition, it takes the longest time to generate road lanes, which are the main construction targets. In this study, the point cloud of the road lane markings, in which color types(white, blue, and yellow) were predicted through the PointNet model pre-trained in previous studies, were used as input data. Based on the point cloud, this study proposed a methodology for automatically drawing and structural editing of the layer of road lane markings. To verify the usability of the 3D vector data constructed through the proposed methodology, the accuracy was analyzed according to the quality inspection criteria of high-definition road maps. In the positional accuracy test of the vector data, the RMSE (Root Mean Square Error) for horizontal and vertical errors were within 0.1m to verify suitability. In the structural editing accuracy test of the vector data, the structural editing accuracy of the road lane markings type and kind were 88.235%, respectively, and the usability was verified. Therefore, it was found that the methodology proposed in this study can efficiently construct vector data of road lanes for high-definition road maps.