Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
WANG, S. ROHDIN, J. PLCHOT, O. BURGET, L. YU, K. ČERNOCKÝ, J.
Originální název
Investigation of Specaugment for Deep Speaker Embedding Learning
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
SpecAugment is a newly proposed data augmentation method for speech recognition. By randomly masking bands in the log Mel spectogram this method leads to impressive performance improvements. In this paper, we investigate the usage of SpecAugment for speaker verification tasks. Two different models, namely 1-D convolutional TDNN and 2-D convolutional ResNet34, trained with either Softmax or AAM-Softmax loss, are used to analyze SpecAugments effectiveness. Experiments are carried out on the Voxceleb and NIST SRE 2016 dataset. By applying SpecAugment to the original clean data in an on-the-fly manner without complex off-line data augmentation methods, we obtained 3.72% and 11.49% EER for NIST SRE 2016 Cantonese and Tagalog, respectively. For Voxceleb1 evaluation set, we obtained 1.47% EER.
Klíčová slova
speaker embedding, on-the-fly data augmentation, speaker verification, specaugment
Autoři
WANG, S.; ROHDIN, J.; PLCHOT, O.; BURGET, L.; YU, K.; ČERNOCKÝ, J.
Vydáno
4. 5. 2020
Nakladatel
IEEE Signal Processing Society
Místo
Barcelona
ISBN
978-1-5090-6631-5
Kniha
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Strany od
7139
Strany do
7143
Strany počet
5
URL
https://ieeexplore.ieee.org/document/9053481/authors#authors
BibTex
@inproceedings{BUT163947, author="WANG, S. and ROHDIN, J. and PLCHOT, O. and BURGET, L. and YU, K. and ČERNOCKÝ, J.", title="Investigation of Specaugment for Deep Speaker Embedding Learning", booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings", year="2020", pages="7139--7143", publisher="IEEE Signal Processing Society", address="Barcelona", doi="10.1109/ICASSP40776.2020.9053481", isbn="978-1-5090-6631-5", url="https://ieeexplore.ieee.org/document/9053481/authors#authors" }