{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00224441","sets":["1164:5159:11151:11203"]},"path":["11203"],"owner":"44499","recid":"224441","title":["Domain Adaptation for Improving End-to-end ASR Performance of Classroom Speech with Variable Recording Condition"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-21"},"_buckets":{"deposit":"9ff35cde-a889-4cff-837f-5391c09437bb"},"_deposit":{"id":"224441","pid":{"type":"depid","value":"224441","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Domain Adaptation for Improving End-to-end ASR Performance of Classroom Speech with Variable Recording Condition","author_link":["591877","591875","591876","591874","591873","591872"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Domain Adaptation for Improving End-to-end ASR Performance of Classroom Speech with Variable Recording Condition"},{"subitem_title":"Domain Adaptation for Improving End-to-end ASR Performance of Classroom Speech with Variable Recording Condition","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"SP2:音声認識","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2023-02-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Science and Technology, Shizuoka University"},{"subitem_text_value":"Faculty of Engineering, Shizuoka University"},{"subitem_text_value":"Graduate School of Science and Technology, Shizuoka University"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Science and Technology, Shizuoka University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Engineering, Shizuoka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Science and Technology, Shizuoka 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/224441/files/IPSJ-SLP23146044.pdf","label":"IPSJ-SLP23146044.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP23146044.pdf","filesize":[{"value":"1.3 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"22"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"bb333fa6-99a1-46de-b55d-0de66cec6aba","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":"Raufun, Nahr"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"ino, Suzuki"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Atsuhiko, Kai"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Raufun, Nahr","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"ino, Suzuki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Atsuhiko, Kai","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":"Automatic speech recognition (ASR) of real-world speech recorded in real environment has been a challenge in the field of artificial intelligence (AI). The real environment speech can vary in terms of location, recording medium and devices and so on. In this research, we particularly take interest in recognizing data recorded in university classroom. This real-world classroom situation is simulated by re-recording a small amount of data in classroom by playing through loudspeaker and recording them using low-quality wireless microphone. Previous research on supervised training of ASR indicates the requirement of large-scale transcribed data in target environment. However, it is costly to record and transcribe such amount of data for desired environment. Therefore, we adopt DNN-based data augmentation method for end-to-end ASR model as well as self-supervised-learning (SSL) based feature extraction with implicit end-to-end model to perform ASR task for classroom data. Fine-tuning of SSL-based ASR using target domain data helps achieving 17.9% character error rate for low audibility data.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Automatic speech recognition (ASR) of real-world speech recorded in real environment has been a challenge in the field of artificial intelligence (AI). The real environment speech can vary in terms of location, recording medium and devices and so on. In this research, we particularly take interest in recognizing data recorded in university classroom. This real-world classroom situation is simulated by re-recording a small amount of data in classroom by playing through loudspeaker and recording them using low-quality wireless microphone. Previous research on supervised training of ASR indicates the requirement of large-scale transcribed data in target environment. However, it is costly to record and transcribe such amount of data for desired environment. Therefore, we adopt DNN-based data augmentation method for end-to-end ASR model as well as self-supervised-learning (SSL) based feature extraction with implicit end-to-end model to perform ASR task for classroom data. Fine-tuning of SSL-based ASR using target domain data helps achieving 17.9% character error rate for low audibility data.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"44","bibliographicVolumeNumber":"2023-SLP-146"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:24:01.861925+00:00","updated":"2025-01-19T13:09:04.543199+00:00","id":224441}