Conference paper

GRÉZL František and KARAFIÁT Martin. Adapting Multilingual Neural Network Hierarchy to a New Language. In: Proceedings of the 4th International Workshop on Spoken Language Technologies for Under- resourced Languages SLTU-2014. – St. Petersburg, Russia, 2014. St. Petersburg: International Speech Communication Association, 2014, pp. 39-45. ISBN 978-5-8088-0908-6.
Publication language:english
Original title:Adapting Multilingual Neural Network Hierarchy to a New Language
Title (cs):Adaptace multilingvální hierarchie neuronových sítí pro nový jazyk
Pages:39-45
Proceedings:Proceedings of the 4th International Workshop on Spoken Language Technologies for Under- resourced Languages SLTU-2014. – St. Petersburg, Russia, 2014
Conference:The 4th International Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU'14)
Place:St. Petersburg, RU
Year:2014
ISBN:978-5-8088-0908-6
Publisher:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2014/grezl_sltu2014_multiling_adapt_p39_45.pdf [PDF]
Keywords
feature extraction, Bottle-Neck features, neural network adaptation, multilingual neural networks, Stacked Bottle- Neck structure
Annotation
This work addresses a thorough evaluation of multilingual techniques for adapting feature extraction neural network hierarchy - Stack Bottle-Neck system.
Abstract
The neural network based features became an inseparable part of state-of-the-art LVCSR systems. With the increasing accent on fast development of ASR system on limited resources, there is an effort to alleviate the need of large amount of transcribed in-domain data. One successful way is to use data from other languages. We present extensive evaluation of several strategies to adapt hierarchical neural network in search for the most effective one. To avoid the bias towards one target language, our strategies were evaluated on five languages. Also, several multilingual neural network hierarchies were trained on two sets of languages. Thus the results provide solid insight into the problem of adapting hierarchical system.
BibTeX:
@INPROCEEDINGS{
   author = {Franti{\v{s}}ek Gr{\'{e}}zl and Martin Karafi{\'{a}}t},
   title = {Adapting Multilingual Neural Network Hierarchy to a New
	Language},
   pages = {39--45},
   booktitle = {Proceedings of the 4th International Workshop on Spoken
	Language Technologies for Under- resourced Languages
	SLTU-2014. – St. Petersburg, Russia, 2014},
   year = {2014},
   location = {St. Petersburg, RU},
   publisher = {International Speech Communication Association},
   ISBN = {978-5-8088-0908-6},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10565}
}

Your IPv4 address: 54.224.13.210
Switch to IPv6 connection

DNSSEC [dnssec]