magyar

Reducing the Inter-speaker Variance of CNN Acoustic Models Using Unsupervised Adversarial Multi-task Training

Tóth, László, Gosztolya, Gábor: Reducing the Inter-speaker Variance of CNN Acoustic Models Using Unsupervised Adversarial Multi-task Training.
In: Speech and Computer. Springer International Publishing, Berlin, pp. 481-490. (2019) ISBN 9783030260613; 9783030260606

[img] Text
2019-specom-adversarial.pdf - Published Version
Closed access: Repository staff only
Download (334kB) | Request a copy
Item Type: Book Section
Date: 2019
Number: 11658
Number of Pages: 10
Page Range: pp. 481-490
ISBN: 9783030260613; 9783030260606
Publisher: Springer International Publishing
Place of Publication: Berlin
Faculty: Faculty of Science and Informatics
Institution: Szegedi Tudományegyetem
MTMT id: 30768490
DOI id: https://doi.org/10.1007/978-3-030-26061-3_49
Related URLs:
Date Deposited: 2019. Nov. 11. 09:53
Last Modified: 2019. Nov. 11. 09:53
URI: http://publicatio.bibl.u-szeged.hu/id/eprint/17307

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.