Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134185" target="_blank" >RIV/00216305:26230/19:PU134185 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/8682918" target="_blank" >https://ieeexplore.ieee.org/document/8682918</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP.2019.8682918" target="_blank" >10.1109/ICASSP.2019.8682918</a>
Alternative languages
Result language
angličtina
Original language name
Transfer Learning Of Language-independent End-to-end ASR With Language Model Fusion
Original language description
This work explores better adaptation methods to low-resource lan-guages using an external language model (LM) under the frame-work of transfer learning. We first build a language-independentASR system in a unified sequence-to-sequence (S2S) architecturewith a shared vocabulary among all languages. During adaptation,we performLM fusion transfer, where an external LM is integratedinto the decoder network of the attention-based S2S model in thewhole adaptation stage, to effectively incorporate linguistic contextof the target language. We also investigate various seed models fortransfer learning. Experimental evaluations using the IARPA BA-BEL data set show that LM fusion transfer improves performanceson all target five languages compared with simple transfer learningwhen the external text data is available. Our final system drasticallyreduces the performance gap from the hybrid systems.
Czech name
—
Czech description
—
Classification
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)
Result continuities
Project
<a href="/en/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of ICASSP
ISBN
978-1-5386-4658-8
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
6096-6100
Publisher name
IEEE Signal Processing Society
Place of publication
Brighton
Event location
Brighton
Event date
May 12, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000482554006065