{"created":"2025-01-19T01:31:28.486542+00:00","updated":"2025-01-19T10:49:43.314662+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00231272","sets":["1164:4179:11237:11430"]},"path":["11430"],"owner":"44499","recid":"231272","title":["Enhancing Dysarthric Speech Recognition with Auxiliary Feature Fusion Module: Exploring Articulatory-related Features from Foundation Models"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-25"},"_buckets":{"deposit":"9277f23f-8960-4e2b-8f55-c4b0007d218a"},"_deposit":{"id":"231272","pid":{"type":"depid","value":"231272","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Enhancing Dysarthric Speech Recognition with Auxiliary Feature Fusion Module: Exploring Articulatory-related Features from Foundation Models","author_link":["624117","624122","624120","624115","624119","624121","624116","624118"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Enhancing Dysarthric Speech Recognition with Auxiliary Feature Fusion Module: Exploring Articulatory-related Features from Foundation Models"},{"subitem_title":"Enhancing Dysarthric Speech Recognition with Auxiliary Feature Fusion Module: Exploring Articulatory-related Features from Foundation Models","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ポスター","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-11-25","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University／Graduate School of Engineering, The University of Tokyo"},{"subitem_text_value":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University"},{"subitem_text_value":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo"},{"subitem_text_value":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University / Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University","subitem_text_language":"en"},{"subitem_text_value":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin 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/231272/files/IPSJ-NL23258014.pdf","label":"IPSJ-NL23258014.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL23258014.pdf","filesize":[{"value":"1.7 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"ebd13435-e575-421b-b275-13dbd18f42c7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuqin, Lin"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Longbiao, Wang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jianwu, Dang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuqin, Lin","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Longbiao, Wang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jianwu, Dang","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Nobuaki, Minematsu","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10115061","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":"2188-8779","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Addressing dysarthric speech variability in Automatic Speech Recognition (ASR) is crucial for improving human-computer interactions for everyone. This paper proposes the Auxiliary Features Fusion (AFFusion) module, which leverages phonetic and articulatory-related features from models like wav2vec to compensate for distorted acoustics in dysarthric ASR. Experimental results using AFFusion with various feature models demonstrate its effectiveness on dysarthric databases. Interestingly, the analysis suggests that AFFusion shares similarities with human speech perception processes, offering potential insights into addressing fuzzy recognition in dysarthric ASR based on the motor theory of speech perception.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Addressing dysarthric speech variability in Automatic Speech Recognition (ASR) is crucial for improving human-computer interactions for everyone. This paper proposes the Auxiliary Features Fusion (AFFusion) module, which leverages phonetic and articulatory-related features from models like wav2vec to compensate for distorted acoustics in dysarthric ASR. Experimental results using AFFusion with various feature models demonstrate its effectiveness on dysarthric databases. Interestingly, the analysis suggests that AFFusion shares similarities with human speech perception processes, offering potential insights into addressing fuzzy recognition in dysarthric ASR based on the motor theory of speech perception.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告自然言語処理（NL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-11-25","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"14","bibliographicVolumeNumber":"2023-NL-258"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":231272,"links":{}}