Investigation of Specaugment for Deep Speaker Embedding Learning
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F20%3APU136464" target="_blank" >RIV/00216305:26230/20:PU136464 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/9053481/authors#authors" target="_blank" >https://ieeexplore.ieee.org/document/9053481/authors#authors</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP40776.2020.9053481" target="_blank" >10.1109/ICASSP40776.2020.9053481</a>
Alternative languages
Result language
angličtina
Original language name
Investigation of Specaugment for Deep Speaker Embedding Learning
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISBN
978-1-5090-6631-5
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
7139-7143
Publisher name
IEEE Signal Processing Society
Place of publication
Barcelona
Event location
Barcelona
Event date
May 4, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000615970407081