Search Results for author:
Found 8 papers, 4 papers with code
VOTE400(Voide Of The Elderly 400 Hours): A Speech Dataset to Study Voice Interface for Elderly-Care
This paper introduces a large-scale Korean speech dataset, called VOTE400, that can be used for analyzing and recognizing voices of the elderly people.
Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity
In this paper, we present an automatic gesture generation model that uses the multimodal context of speech text, audio, and speaker identity to reliably generate gestures.
Ranked #2 on
Gesture Generation
on BEAT
AIR-Act2Act: Human-human interaction dataset for teaching non-verbal social behaviors to robots
In addition, we provide the joint angles of a humanoid NAO robot which are converted from the human behavior that robots need to learn.
Robotics
ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly
To cope with this situation, we introduce a new dataset called ETRI-Activity3D, focusing on the daily activities of the elderly in robot-view.
Cut-and-Paste Dataset Generation for Balancing Domain Gaps in Object Instance Detection
Then, we show that the original cut-and-paste approach suffers from a new domain gap problem, an unbalanced domain gaps, because it has two separate source domains for foreground and background, unlike the conventional domain shift problem.
Neural Networks with Activation Networks
This work presents an adaptive activation method for neural networks that exploits the interdependency of features.
Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots
Co-speech gestures enhance interaction experiences between humans as well as between humans and robots.
Robotics
Deep Asymmetric Networks with a Set of Node-wise Variant Activation Functions
As a result, features learned by the nodes are sorted by the node indices in the order of their importance.
