The University of Edinburgh Head-Motion and Audio Storytelling (UoE-HAS) Dataset

David A. Braude; Hiroshi Shimodaira; Atef Ben Youssef

The University of Edinburgh Head-Motion and Audio Storytelling (UoE-HAS) Dataset

David A. Braude, Hiroshi Shimodaira, Atef Ben Youssef

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

In this paper we announce the release of a large dataset of storytelling monologue with motion capture for the head and body. Initial tests on the dataset indicate that head motion is more dependant on the speaker than the style of speech.

Original language	Undefined/Unknown
Title of host publication	Proc. of Intelligent Virtual Agents
Pages	466-467
Number of pages	2
Publication status	Published - 2013

Access to Document

UofE Head-Motion and Audio StorytellingAccepted author manuscript, 82.6 KB

Cite this

@inproceedings{cc12d9b18d1f49088b6233ac866aef9d,

title = "The University of Edinburgh Head-Motion and Audio Storytelling (UoE-HAS) Dataset",

abstract = "In this paper we announce the release of a large dataset of storytelling monologue with motion capture for the head and body. Initial tests on the dataset indicate that head motion is more dependant on the speaker than the style of speech.",

author = "Braude, {David A.} and Hiroshi Shimodaira and {Ben Youssef}, Atef",

year = "2013",

language = "Undefined/Unknown",

pages = "466--467",

booktitle = "Proc. of Intelligent Virtual Agents",

}

TY - GEN

T1 - The University of Edinburgh Head-Motion and Audio Storytelling (UoE-HAS) Dataset

AU - Braude, David A.

AU - Shimodaira, Hiroshi

AU - Ben Youssef, Atef

PY - 2013

Y1 - 2013

N2 - In this paper we announce the release of a large dataset of storytelling monologue with motion capture for the head and body. Initial tests on the dataset indicate that head motion is more dependant on the speaker than the style of speech.

AB - In this paper we announce the release of a large dataset of storytelling monologue with motion capture for the head and body. Initial tests on the dataset indicate that head motion is more dependant on the speaker than the style of speech.

M3 - Conference contribution

SP - 466

EP - 467

BT - Proc. of Intelligent Virtual Agents

ER -