Publication Details

Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting

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
Czech title
Struktury pro extrakci bottle-neck parametrů pro multilingvální trénování a přenos mezi jazyky
Type
conference paper
Language
english
Authors
URL
Keywords

DNN topology; Stacked Bottle-Neck; feature extraction; multilingual training; system porting

Abstract

This article describes the Bottle-Neck feature extraction structures for multilingual training and porting.

Annotation

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.

Published
2016
Pages
144-151
Journal
Procedia Computer Science, vol. 2016, no. 81, ISSN 1877-0509
Proceedings
Procedia Computer Science
Conference
The 5th International Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU'16), Yogyakarta, ID
Publisher
Elsevier Science
Place
Yogyakarta, ID
DOI
UT WoS
000387446500020
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB11182,
   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",
   doi = "10.1016/j.procs.2016.04.042",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11182"
}
Back to top