WEKO3
-
RootNode
アイテム
Adapting multilingual speech representation model for a new, underresourced language through multilingual fine-tuning and continued pretraining
https://kitami-it.repo.nii.ac.jp/records/2000562
https://kitami-it.repo.nii.ac.jp/records/20005629d7f859e-5bd9-4d68-bd47-4a30ad5eca91
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
2301.07295.pdf (524 KB)
|
|
| 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 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
| 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
× 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 | |||||||||||||
Share
Cite as
Karol Nowakowski, Michal Ptaszynski, Kyoko Murasaki, Jagna Nieuważny, n.d., Adapting multilingual speech representation model for a new, underresourced language through multilingual fine-tuning and continued pretraining: Elsevier.
Loading...
