{"created":"2025-01-19T01:33:27.463102+00:00","links":{},"updated":"2025-01-19T10:24:56.926204+00:00","id":232534,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00232534","sets":["1164:5159:11541:11549"]},"path":["11549"],"owner":"44499","recid":"232534","title":["Low-resource Speech Recognition using Hierarchical CTC and Large Pre-trained Model"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-02-22"},"_buckets":{"deposit":"afe86201-d9ca-4809-b489-c6875f8a80e7"},"_deposit":{"id":"232534","pid":{"type":"depid","value":"232534","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Low-resource Speech Recognition using Hierarchical CTC and Large Pre-trained Model","author_link":["629627","629628","629630","629629"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Low-resource Speech Recognition using Hierarchical CTC and Large Pre-trained Model"},{"subitem_title":"Low-resource Speech Recognition using Hierarchical CTC and Large Pre-trained Model","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ポスターセッション2 SP/SLP","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2024-02-22","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Informatics, Kyoto University"},{"subitem_text_value":"Graduate School of Informatics, Kyoto University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Informatics, Kyoto University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Informatics, Kyoto University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/232534/files/IPSJ-SLP24151064.pdf","label":"IPSJ-SLP24151064.pdf"},"date":[{"dateType":"Available","dateValue":"2026-02-22"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP24151064.pdf","filesize":[{"value":"1.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"5918e208-5c97-4c97-b66a-39c2bc825805","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Jaeyoung, Lee"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tatsuya, Kawahara"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Jaeyoung, Lee","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tatsuya, Kawahara","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10442647","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8663","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"The performance of automatic speech recognition (ASR) for low-resource languages has seen significant improvement, owing to the recent advancements in large-scale pre-training and fine-tuning paradigms. This study investigates optimizing fine-tuning for low-resource languages, utilizing hierarchical intermediate connectionist temporal classification (CTC). This approach employs target units of varying granularity, from subwords to phonemes, across different CTC losses, taking advantage of the hierarchical linguistic structure of natural languages. We apply this technique to the fine-tuning of a large pre-trained model, investigating the conditions under which it is most effective.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The performance of automatic speech recognition (ASR) for low-resource languages has seen significant improvement, owing to the recent advancements in large-scale pre-training and fine-tuning paradigms. This study investigates optimizing fine-tuning for low-resource languages, utilizing hierarchical intermediate connectionist temporal classification (CTC). This approach employs target units of varying granularity, from subwords to phonemes, across different CTC losses, taking advantage of the hierarchical linguistic structure of natural languages. We apply this technique to the fine-tuning of a large pre-trained model, investigating the conditions under which it is most effective.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2024-02-22","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"64","bibliographicVolumeNumber":"2024-SLP-151"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}