SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1810.12541 · 2018

Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 16 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ehwa009/Co-Speech_Gesture_Generation reimplementation 2 of 2
youngwoo-yoon/youtube-gesture-dataset pwc_unofficial 1 of 12
pieterwolfert/co-speech-humanoids reimplementation 1 of 2
FunctionStatusWhere it lives
encodeinputstring Ran pieterwolfert/co-speech-humanoids/inference.py
pointer only (licence: NONE) · get_code("c4246a111279f4bf")
get_pad_mask Ran ehwa009/Co-Speech_Gesture_Generation/transformer/models.py
code served (permissive licence) · get_code("da23fd901ddaf194")
get_subsequent_mask Ran ehwa009/Co-Speech_Gesture_Generation/transformer/models.py
code served (permissive licence) · get_code("b84290f81844cc1c")
unicode_to_ascii Ran youngwoo-yoon/youtube-gesture-dataset/script/make_ted_dataset.py
code served (permissive licence) · get_code("3b0218c9534b6ee7")
draw_skeleton_on_image Not yet run youngwoo-yoon/youtube-gesture-dataset/script/data_utils.py
code served (permissive licence) · get_code("76294a3b3ad8a25b")
get_closest_skeleton Not yet run youngwoo-yoon/youtube-gesture-dataset/script/data_utils.py
code served (permissive licence) · get_code("b8fce4e5f8180782")
get_vid_from_filename Not yet run youngwoo-yoon/youtube-gesture-dataset/script/run_openpose.py
code served (permissive licence) · get_code("ac8986943eac334d")
is_list_empty Not yet run youngwoo-yoon/youtube-gesture-dataset/script/data_utils.py
code served (permissive licence) · get_code("eedbb532217dcb7f")
normalize_skeleton Not yet run youngwoo-yoon/youtube-gesture-dataset/script/motion_preprocessor.py
code served (permissive licence) · get_code("47e5434a74faaa2f")
normalize_string Not yet run youngwoo-yoon/youtube-gesture-dataset/script/make_ted_dataset.py
code served (permissive licence) · get_code("61474285bf6c43cc")
read_sceneinfo Not yet run youngwoo-yoon/youtube-gesture-dataset/script/run_clip_filtering.py
code served (permissive licence) · get_code("b7fe79023c1fb93b")
read_skeleton_json Not yet run youngwoo-yoon/youtube-gesture-dataset/script/run_openpose.py
code served (permissive licence) · get_code("5b4fc0454f5233d4")
read_subtitle Not yet run youngwoo-yoon/youtube-gesture-dataset/script/make_ted_dataset.py
code served (permissive licence) · get_code("b4d548c56111c912")
run_filtering Not yet run youngwoo-yoon/youtube-gesture-dataset/script/run_clip_filtering.py
code served (permissive licence) · get_code("00c7dd2d57e0080f")
speech2gesture Not yet run pieterwolfert/co-speech-humanoids/inference.py
pointer only (licence: NONE) · get_code("8587006901a615dd")
video_filter Not yet run youngwoo-yoon/youtube-gesture-dataset/script/download_video.py
code served (permissive licence) · get_code("79171f8ed610e990")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Co-speech gestures enhance interaction experiences between humans as well as between humans and robots. Existing robots use rule-based speech-gesture association, but this requires human labor and prior knowledge of experts to be implemented. We present a learning-based co-speech gesture generation that is learned from 52 h of TED talks. The proposed end-to-end neural network model consists of an encoder for speech text understanding and a decoder to generate a sequence of gestures. The model successfully produces various gestures including iconic, metaphoric, deictic, and beat gestures. In a subjective evaluation, participants reported that the gestures were human-like and matched the speech content. We also demonstrate a co-speech gesture with a NAO robot working in real time.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1810.12541")
get_code_for_paper("1810.12541")
have("1810.12541")

Connect an agent — have() is free.