Analysis of Multilingual BLSTM Acoustic Model on Lowand High Resource Languages

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130734" target="_blank" >RIV/00216305:26230/18:PU130734 - isvavai.cz</a>

Result on the web

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11720" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11720</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2018.8462083" target="_blank" >10.1109/ICASSP.2018.8462083</a>

Result language

angličtina

Original language name

Analysis of Multilingual BLSTM Acoustic Model on Lowand High Resource Languages

Original language description

The paper provides an analysis of automatic speech recognition systems (ASR) based on multilingual BLSTM, where we used multi-task training with separate classification layer for each language. The focus is on low resource languages, where only a limited amount of transcribed speech is available. In such scenario, we found it essential to train the ASR systems in a multilingual fashion and we report superior results obtained with pre-trained multilingual BLSTM on this task. The high resource languages are also taken into account and we show the importance of language richness for multilingual training. Next, we present the performance of this technique as a function of amount of target language data. The importance of including context information into BLSTM multilingual systems is also stressed, and we report increased resilience of large NNs to overtraining in case of multi-task training.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of ICASSP 2018

ISBN

978-1-5386-4658-8

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

5789-5793

Publisher name

IEEE Signal Processing Society

Place of publication

Calgary

Event location

Calgary

Event date

Apr 15, 2018

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

000446384605189