magyar

Adversarial Multi-task Learning of Speaker-invariant Deep Neural Network Acoustic Models for Speech Recognition

Tóth László and Gosztolya Gábor: Adversarial Multi-task Learning of Speaker-invariant Deep Neural Network Acoustic Models for Speech Recognition.
In: Proceedings of the 1st International Conference on Advances in Signal Processing and Artificial Intelligence. IFSA Publishing, Barcelona, pp. 82-86. (2019) ISBN 9788409101276

[thumbnail of 2019-aspai.pdf] Text
2019-aspai.pdf - Published Version
Closed access: Repository staff only
Download (916kB) | Request a copy
[thumbnail of 30768490_címlap_tartj.pdf] Text
30768490_címlap_tartj.pdf - Published Version
Closed access: Repository staff only
Download (450kB) | Request a copy
Creators:
Tóth László MTMT
Gosztolya Gábor MTMT
Item Type: Book Section
Date: 2019
Number of Pages: 5
Page Range: pp. 82-86
ISBN: 9788409101276
Publisher: IFSA Publishing
Place of Publication: Barcelona
Faculty/Unit: Faculty of Science and Informatics
Institution: University of Szeged (2000-)
Language: English
MTMT rekordazonosító: 30774087
Date Deposited: 2019. Nov. 11. 10:37
Last Modified: 2019. Nov. 11. 10:37
URI: http://publicatio.bibl.u-szeged.hu/id/eprint/17306

Actions (login required)

View Item View Item
Download Statistics

Downloads

Downloads per month over past year

Technical information: publicatio AT ek.szte.hu
SZTE Repository of Publications is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.