activity
20182022
most citedSpeech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity

321 citations · 342 across the 4 of their papers we have counts for

collaborators

7 papers

cs.RO2022

Nonverbal Social Behavior Generation for Social Robots Using End-to-End Learning

Woo-Ri Ko, Minsu Jang, Jaeyeon Lee +1

To provide effective and enjoyable human-robot interaction, it is important for social robots to exhibit nonverbal behaviors, such as a handshake or a hug. However, the traditional…

cs.HC202120 cited

SGToolkit: An Interactive Gesture Authoring Toolkit for Embodied Conversational Agents

Youngwoo Yoon, Keunwoo Park, Minsu Jang +2

Non-verbal behavior is essential for embodied agents like social robots, virtual avatars, and digital humans. Existing behavior authoring approaches including keyframe animation an…

eess.AS20211 cited

VOTE400(Voide Of The Elderly 400 Hours): A Speech Dataset to Study Voice Interface for Elderly-Care

Minsu Jang, Sangwon Seo, Dohyung Kim +3

This paper introduces a large-scale Korean speech dataset, called VOTE400, that can be used for analyzing and recognizing voices of the elderly people. The dataset includes about 3…

cs.GR2020321 cited

Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity

Youngwoo Yoon, Bok Cha, Joo-Haeng Lee +4

For human-like agents, including virtual avatars and social robots, making proper gestures while speaking is crucial in human--agent interaction. Co-speech gestures enhance interac…

cs.RO2020

ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly

Jinhyeok Jang, Dohyung Kim, Cheonshu Park +3

Deep learning, based on which many modern algorithms operate, is well known to be data-hungry. In particular, the datasets appropriate for the intended application are difficult to…

cs.RO2019

Cut-and-Paste Dataset Generation for Balancing Domain Gaps in Object Instance Detection

Woo-han Yun, Taewoo Kim, Jaeyeon Lee +2

Training an object instance detector where only a few training object images are available is a challenging task. One solution is a cut-and-paste method that generates a training d…