Coarse-To-Fine And Cross-Lingual ASR Transfer

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440570" target="_blank" >RIV/00216208:11320/21:10440570 - isvavai.cz</a>
Result on the web
<a href="https://ics.upjs.sk/~antoni/ceur-ws.org/Vol-0000/paper09.pdf" target="_blank" >https://ics.upjs.sk/~antoni/ceur-ws.org/Vol-0000/paper09.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Coarse-To-Fine And Cross-Lingual ASR Transfer
Original language description
End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results but they require large datasets and extensive computing resources. Transfer learning has been proposed to overcome these difficulties even across languages, e.g., German ASR trained from an English model. We experiment with much less related languages, reusing an English model for Czech ASR. To simplify the transfer, we propose to use an intermediate alphabet, Czech without accents, and we document that it is a highly effective strategy. The technique is also useful on Czech data alone, in the style of "coarse-to-fine" training. We achieve substantial reductions in training time as well as word error rate (WER).
Czech name
—
Czech description
—

Type
O - Miscellaneous
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
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)