Conference paper

GRÉZL František and KARAFIÁT Martin. Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting. In: Procedia Computer Science. Yogyakarta: Elsevier Science, 2016, pp. 144-151. ISSN 1877-0509. Available from: http://ac.els-cdn.com/S1877050916300564/1-s2.0-S1877050916300564-main.pdf?_tid=86f349d0-241e-11e6-9aa8-00000aab0f6b&acdnat=1464362601_c282a52b5e30264cf0bbd7b0e0d440ba
Publication language:english
Original title:Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting
Title (cs):Struktury pro extrakci bottle-neck parametrů pro multilingvální trénování a přenos mezi jazyky
Pages:144-151
Proceedings:Procedia Computer Science
Conference:The 5th International Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU'16)
Place:Yogyakarta, ID
Year:2016
URL:http://ac.els-cdn.com/S1877050916300564/1-s2.0-S1877050916300564-main.pdf?_tid=86f349d0-241e-11e6-9aa8-00000aab0f6b&acdnat=1464362601_c282a52b5e30264cf0bbd7b0e0d440ba
Journal:Procedia Computer Science, Vol. 2016, No. 81, CZ
ISSN:1877-0509
Publisher:Elsevier Science
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2016/grezl_sltu2016_26-8046.pdf [PDF]
Files: 
+Type Name Title Size Last modified
icongrezl_sltu2016_26-8046.pdf138 KB2017-03-06 10:57:28
^ Select all
With selected:
Keywords
DNN topology; Stacked Bottle-Neck; feature extraction; multilingual training; system porting
Annotation
This article describes the Bottle-Neck feature extraction structures for multilingual training and porting.
Abstract
Stacked-Bottle-Neck (SBN) feature extraction is a crucial part of modern automatic speech recognition (ASR) systems. The SBN network traditionally contains a hidden layer between the BN and output layers. Recently, we have observed that an SBN architecture without this hidden layer (i.e. direct BN-layer - output-layer connection) performs better for a single language but fails in scenarios where a network pre-trained in multilingual fashion is ported to a target language. In this paper, we describe two strategies allowing the direct-connection SBN network to indeed benefit from pre-training with a multilingual net: (1) pre-training multilingual net with the hidden layer which is discarded before porting to the target language and (2) using only the the direct- connection SBN with triphone targets both in multilingual pre-training and porting to the target language. The results are reported on IARPA-BABEL limited language pack (LLP) data.
BibTeX:
@INPROCEEDINGS{
   author = {Franti{\v{s}}ek Gr{\'{e}}zl and Martin Karafi{\'{a}}t},
   title = {Bottle-Neck Feature Extraction Structures for Multilingual
	Training and Porting},
   pages = {144--151},
   booktitle = {Procedia Computer Science},
   journal = {Procedia Computer Science},
   volume = {2016},
   number = {81},
   year = {2016},
   location = {Yogyakarta, ID},
   publisher = {Elsevier Science},
   ISSN = {1877-0509},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11182}
}

Your IPv4 address: 54.166.19.237
Switch to IPv6 connection

DNSSEC [dnssec]