Publication Details
Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting
DNN topology; Stacked Bottle-Neck; feature extraction; multilingual training; system porting
This article describes the Bottle-Neck feature extraction structures for multilingual training and porting.
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.
@inproceedings{BUT130985,
author="František {Grézl} and Martin {Karafiát}",
title="Bottle-Neck Feature Extraction Structures for Multilingual Training and Porting",
booktitle="Procedia Computer Science",
year="2016",
journal="Procedia Computer Science",
volume="2016",
number="81",
pages="144--151",
publisher="Elsevier Science",
address="Yogyakarta",
doi="10.1016/j.procs.2016.04.042",
issn="1877-0509",
url="http://ac.els-cdn.com/S1877050916300564/1-s2.0-S1877050916300564-main.pdf?_tid=86f349d0-241e-11e6-9aa8-00000aab0f6b&acdnat=1464362601_c282a52b5e30264cf0bbd7b0e0d440ba"
}