Naver Corporation

About: Naver Corporation is a company organization based out in Seongnam-si, South Korea. It is known for research contribution in the topics: Terminal (electronics) & Computer science. The organization has 4038 authors who have published 4294 publications receiving 35045 citations. The organization is also known as: NAVER Corporation & NAVER.

Data-Driven Harmonic Filters for Audio Representation Learning

Abstract: We introduce a trainable front-end module for audio representation learning that exploits the inherent harmonic structure of audio signals. The proposed architecture, composed of a set of filters, compels the subsequent network to capture harmonic relations while preserving spectro-temporal locality. Since the harmonic structure is known to have a key role in human auditory perception, one can expect these harmonic filters to yield more efficient audio representations. Experimental results show that a simple convolutional neural network back-end with the proposed front-end outperforms state-of-the-art baseline methods in automatic music tagging, keyword spotting, and sound event tagging tasks.

Effect of Pinitol on Glucose Metabolism and Adipocytokines in Uncontrolled Type 2 Diabetes Mellitus

Abstract: Pinitol (3-O-methyl-D-chiro-inositol) was identified in putative insulin mediator fractions that have hypoglycemic activity, and appears to mimic the act effects of insulin by acting downstream in the insulin signaling pathway. We evaluated the effect of pinitol therapy in type 2 diabetic patients who were poorly controlled with hypoglycemic drugs, such as sulfonylurea, metformin and/or insulin. Twenty type 2 diabetic patients were enrolled in our study. Fasting glucose, fasting c-peptide, total cholesterol, triglyceride, and HDLand LDL-cholesterol were checked before and after a 12-week pinitol treatment (20 mg kg 1 day ). All subjects continued their current medications during the study. Adipocytokines, such as adiponectin, leptin, free fatty acids, and c-reactive protein (CRP) were checked before and after pinitol treatment. After pinitol treatment, fasting glucose, post-prandial glucose levels, and hemoglobin A1c were significantly decreased (P < 0.05). Fasting serum adiponectin, leptin, free fatty acid, and CRP levels did not change after pinitol treatment. In the unresponsive group, serum c-peptide levels were higher than in the responsive group. Twelve weeks of pinitol treatment altered glucose metabolism, but not lipid profiles or adipocytokine levels, in type 2 diabetic patients. Additional research is needed to define the physiological and potential therapeutic effects of pinitol administration. # 2007 Published by Elsevier Ireland Ltd.

System and method for providing contents on a network

Abstract: Disclosed is a contents-providing system for receiving contents from a web server and providing the contents to a portable terminal connected via a network that comprises: a user information database for storing user ID information; an authentication server for performing authentication based upon the user ID information by using the user information database when the user ID information and a URL of a web server are input by the portable terminal, and outputting the URL after performing the authentication; and a data server for requesting that the web server corresponding to the URL provided by the authentication server provides the contents, processing the contents provided by the web server into a predetermined format, and transmitting the processed contents to the portable terminal.

FaceFilter: Audio-visual speech separation using still images

Abstract: The objective of this paper is to separate a target speaker's speech from a mixture of two speakers using a deep audio-visual speech separation network. Unlike previous works that used lip movement on video clips or pre-enrolled speaker information as an auxiliary conditional feature, we use a single face image of the target speaker. In this task, the conditional feature is obtained from facial appearance in cross-modal biometric task, where audio and visual identity representations are shared in latent space. Learnt identities from facial images enforce the network to isolate matched speakers and extract the voices from mixed speech. It solves the permutation problem caused by swapped channel outputs, frequently occurred in speech separation tasks. The proposed method is far more practical than video-based speech separation since user profile images are readily available on many platforms. Also, unlike speaker-aware separation methods, it is applicable on separation with unseen speakers who have never been enrolled before. We show strong qualitative and quantitative results on challenging real-world examples.

Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network

Abstract: Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still uncommon. In this study, we carry out extensive experiments to validate that carefully assembling these techniques and applying them to basic CNN models (e.g. ResNet and MobileNet) can improve the accuracy and robustness of the models while minimizing the loss of throughput. Our proposed assembled ResNet-50 shows improvements in top-1 accuracy from 76.3\% to 82.78\%, mCE from 76.0\% to 48.9\% and mFR from 57.7\% to 32.3\% on ILSVRC2012 validation set. With these improvements, inference throughput only decreases from 536 to 312. To verify the performance improvement in transfer learning, fine grained classification and image retrieval tasks were tested on several public datasets and showed that the improvement to backbone network performance boosted transfer learning performance significantly. Our approach achieved 1st place in the iFood Competition Fine-Grained Visual Recognition at CVPR 2019, and the source code and trained models are available at this https URL