Conference paperGRÉZL František and KARAFIÁT Martin. Boosting Performance on Low-resource Languages by Standard Corpora: AN ANALYSIS. In: Proceeding of SLT 2016. San Diego: IEEE Signal Processing Society, 2016, pp. 629-636. ISBN 978-1-5090-4903-5. | Publication language: | english |
---|
Original title: | Boosting Performance on Low-resource Languages by Standard Corpora: AN ANALYSIS |
---|
Title (cs): | Zlepšení úspěšnosti na jazycích s omezenými zdroji pomocí standardních řečových databází: analýza |
---|
Pages: | 629-636 |
---|
Proceedings: | Proceeding of SLT 2016 |
---|
Conference: | 2016 IEEE Workshop on Spoken Language Technology |
---|
Place: | San Diego, US |
---|
Year: | 2016 |
---|
ISBN: | 978-1-5090-4903-5 |
---|
Publisher: | IEEE Signal Processing Society |
---|
URL: | http://www.fit.vutbr.cz/research/groups/speech/publi/2016/grezl_slt2016_0000629.pdf [PDF] |
---|
Keywords |
---|
DNN topology, Stacked Bottle-neck, feature extraction,
multilingual training, system porting, low resource |
Annotation |
---|
In this paper, we have evaluated the multilingual techniques for single
source-language scenario. Since it is hard to obtain coherent
multilingual corpora usable for multilingual training, using single,
well resourced, language instead is quite attractive. |
Abstract |
---|
In this paper, we analyze the feasibility of using single wellresourced
language - English - as a source language for multilingual
techniques in context of Stacked Bottle-Neck tandem system. The
effect of amount of data and number of tied-states in the source
language on performance of ported system is evaluated together
with different porting strategies. Generally, increasing data amount
and level-of-detail both is positive. A greater effect is observed
for increasing number of tied states. The modified neural network
structure, shown useful for multilingual porting, was also evaluated
with its specific porting procedure. Using original NN structure in
combination with modified porting adapt-adapt strategy was fount
as best. It achieves relative improvement 3.5-8.8% on variety of target
languages. These results are comparable with using multilingual
NNs pretrained on 7 languages. |
BibTeX: |
---|
@INPROCEEDINGS{
author = {Franti{\v{s}}ek Gr{\'{e}}zl and Martin
Karafi{\'{a}}t},
title = {Boosting Performance on Low-resource Languages by
Standard Corpora: AN ANALYSIS},
pages = {629--636},
booktitle = {Proceeding of SLT 2016},
year = {2016},
location = {San Diego, US},
publisher = {IEEE Signal Processing Society},
ISBN = {978-1-5090-4903-5},
language = {english},
url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11311}
} |
|