Item type |
学術雑誌論文 / Journal Article(1) |
公開日 |
2024-02-28 |
タイトル |
|
|
タイトル |
Adapting multilingual speech representation model for a new, underresourced language through multilingual fine-tuning and continued pretraining |
|
言語 |
en |
言語 |
|
|
言語 |
eng |
資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
アクセス権 |
|
|
アクセス権 |
open access |
|
アクセス権URI |
http://purl.org/coar/access_right/c_abf2 |
著者 |
Karol Nowakowski
Michal Ptaszynski
Kyoko Murasaki
Jagna Nieuważny
|
抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
In recent years, neural models learned through self-supervised pretraining on large scale multilingual text or speech data have exhibited promising results for underresourced languages, especially when a relatively large amount of data from related language(s) is available. While the technology has a potential for facilitating tasks carried out in language documentation projects, such as speech transcription, pretraining a multilingual model from scratch for every new language would be highly impractical. We investigate the possibility for adapting an existing multilingual wav2vec 2.0 model for a new language, focusing on actual fieldwork data from a critically endangered tongue: Ainu. Specifically, we (i) examine the feasibility of leveraging data from similar languages also in fine-tuning; (ii) verify whether the model’s performance can be improved by further pretraining on target language data. Our results show that continued pretraining is the most effective method to adapt a wav2vec 2.0 model for a new language and leads to considerable reduction in error rates. Furthermore, we find that if a model pretrained on a related speech variety or an unrelated language with similar phonological characteristics is available, multilingual fine-tuning using additional data from that language can have positive impact on speech recognition performance when there is very little labeled data in the target language. |
|
言語 |
en |
書誌情報 |
en : Information Processing & Management
巻 60,
号 2
|
ISSN |
|
|
収録物識別子タイプ |
PISSN |
|
収録物識別子 |
0306-4573 |
DOI |
|
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1016/j.ipm.2022.103148 |
権利 |
|
|
言語 |
en |
|
権利情報 |
c2023 Elsevier Ltd. All rights reserved. |
出版者 |
|
|
出版者 |
Elsevier |
|
言語 |
en |
著者版フラグ |
|
|
言語 |
en |
|
値 |
author |
出版タイプ |
|
|
出版タイプ |
AM |
|
出版タイプResource |
http://purl.org/coar/version/c_ab4af688f83e57aa |