Crossmark

Improving speech embedding using crossmodal transfer learning with audio-visual data

Crossref DOI link: https://doi.org/10.1007/s11042-018-6992-3

Published Online: 2018-12-08

Published Print: 2019-06

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Le, Nam https://orcid.org/0000-0002-0616-0158
Odobez, Jean-Marc
Funding

Funding for this research was provided by:

FP7 Ideas: European Research Council (611057)

Horizon 2020 Framework Programme (688147)
License Information

Text and Data Mining valid from 2018-12-08
More Information

Article History

Received: 14 April 2018

Revised: 13 October 2018

Accepted: 28 November 2018

First Online: 8 December 2018