Hybrid Seq2Seq Architecture for 3D Co-Speech Gesture Generation

Saleh, K

Hybrid Seq2Seq Architecture for 3D Co-Speech Gesture Generation

Saleh, K

Permalink

Publisher:: Association for Computing Machinery (ACM)
Publication Type:: Conference Proceeding
Citation:: ACM International Conference Proceeding Series, 2022, pp. 748-752
Issue Date:: 2022-11-07

Closed Access

	Filename	Description	Size
	Hybrid Seq2Seq Architecture for 3D Co-Speech Gesture Generation.pdf	Published version	768.45 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Saleh, K
dc.date.accessioned	2023-04-20T04:18:50Z
dc.date.available	2023-04-20T04:18:50Z
dc.date.issued	2022-11-07
dc.identifier.citation	ACM International Conference Proceeding Series, 2022, pp. 748-752
dc.identifier.isbn	9781450393904
dc.identifier.uri	http://hdl.handle.net/10453/170030
dc.description.abstract	This paper describes the co-speech gesture generation system developed by DSI team for the GENEA challenge 2022. The proposed framework features a unique hybrid encoder-decoder architecture based on transformer networks and recurrent neural networks. The proposed framework has been trained using only the official training data split of the challenge and its performance has been evaluated on the testing split. The framework has achieved promising results on both the subjective (specially the human-likeness) and objective evaluation metrics.
dc.language	en
dc.publisher	Association for Computing Machinery (ACM)
dc.relation.ispartof	ACM International Conference Proceeding Series
dc.relation.ispartof	INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION
dc.relation.isbasedon	10.1145/3536221.3558064
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Hybrid Seq2Seq Architecture for 3D Co-Speech Gesture Generation
dc.type	Conference Proceeding
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/A/DRsch The Data Science Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2023-04-20T04:18:49Z
pubs.publication-status	Published

Abstract:

This paper describes the co-speech gesture generation system developed by DSI team for the GENEA challenge 2022. The proposed framework features a unique hybrid encoder-decoder architecture based on transformer networks and recurrent neural networks. The proposed framework has been trained using only the official training data split of the challenge and its performance has been evaluated on the testing split. The framework has achieved promising results on both the subjective (specially the human-likeness) and objective evaluation metrics.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/170030