{"links":{},"id":192700,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00192700","sets":["1164:5159:9402:9617"]},"path":["9617"],"owner":"44499","recid":"192700","title":["Feature Transfer Learning for Wav2Text Sequence-to-Sequence ASR"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-12-03"},"_buckets":{"deposit":"2b625aa2-8727-4a9b-8e59-7f51dbc947ca"},"_deposit":{"id":"192700","pid":{"type":"depid","value":"192700","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Feature Transfer Learning for Wav2Text Sequence-to-Sequence ASR","author_link":["450415","450418","450416","450419","450417","450420"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Feature Transfer Learning for Wav2Text Sequence-to-Sequence ASR"},{"subitem_title":"Feature Transfer Learning for Wav2Text Sequence-to-Sequence ASR","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"セッション1 音声認識","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2018-12-03","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP"},{"subitem_text_value":"Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP"},{"subitem_text_value":"Nara Institute of Science and Technology／RIKEN, Center for Advanced Intelligence Project AIP"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP","subitem_text_language":"en"},{"subitem_text_value":"Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP","subitem_text_language":"en"},{"subitem_text_value":"Nara Institute of Science and Technology / RIKEN, Center for Advanced Intelligence Project AIP","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/192700/files/IPSJ-SLP18125003.pdf","label":"IPSJ-SLP18125003.pdf"},"date":[{"dateType":"Available","dateValue":"2020-12-03"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP18125003.pdf","filesize":[{"value":"646.9 kB"}],"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":"f161f955-7722-4efc-bdcc-f89b48a66bf6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Andros, Tjandra"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Sakriani, Sakti"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Satoshi, Nakamura"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Andros, Tjandra","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Sakriani, Sakti","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Satoshi, Nakamura","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":"In this paper, we construct the first end-to-end attention-based encoder-decoder model to process directly from raw speech waveform to the text transcription. We called the model as ”Attention-basedWav2Text”. To assist the training process of the end-to-end model, we propose to utilize a feature transfer learning. Experimental results also reveal that the proposed Attention-based Wav2Text model directly with raw waveform could achieve a better result in comparison with the attentional encoder-decoder model trained on standard front-end filterbank features.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this paper, we construct the first end-to-end attention-based encoder-decoder model to process directly from raw speech waveform to the text transcription. We called the model as ”Attention-basedWav2Text”. To assist the training process of the end-to-end model, we propose to utilize a feature transfer learning. Experimental results also reveal that the proposed Attention-based Wav2Text model directly with raw waveform could achieve a better result in comparison with the attentional encoder-decoder model trained on standard front-end filterbank features.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"2","bibliographic_titles":[{"bibliographic_title":"研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2018-12-03","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"2018-SLP-125"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T00:58:23.679884+00:00","updated":"2025-01-20T00:02:25.179333+00:00"}