• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.11a
• /
• pp.14-15
• /
• 2021

Even though the Al. form system, which was developed to replace the Euro-form, has been used as the slab lower formwork for almost all concrete structures based on the light weight and high conversion rate, the low-noise Drop method has been developed and used in order to overcome the limitations of the Al. Form system such as noise pollution and safety accidents caused by free fall during the demolding. However, as the low-noise drop method is still insufficient, Safety Full Drop Al. Form method is expected to be in the spotlight in the construction market based on its excellent advantages compared to the developed methods. In addition, we plan to conduct research to further contribute to securing the quality of the overall structure through continuous improvement and supplementation by introducing an automation system to the very construction method.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.703-709
• /
• 2019

This paper proposes speech recognition systems employing Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) structures combined with Hidden Markov Moldel (HMM) to effectively recognize the speech of VeloPharyngeal Insufficiency (VPI) patients, and compares the recognition performance of the systems to the Gaussian Mixture Model (GMM-HMM) and fully-connected Deep Neural Network (DNNHMM) based speech recognition systems. In this paper, the initial model is trained using normal speakers' speech and simulated VPI speech is used for generating a prior model for speaker adaptation. For VPI speaker adaptation, selected layers are trained in the CNN-HMM based model, and dropout regulatory technique is applied in the LSTM-HMM based model, showing 3.68 % improvement in recognition accuracy. The experimental results demonstrate that the proposed LSTM-HMM-based speech recognition system is effective for VPI speech with small-sized speech data, compared to conventional GMM-HMM and fully-connected DNN-HMM system.