{"created":"2025-01-19T01:14:55.549425+00:00","updated":"2025-01-19T16:54:20.764591+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00214091","sets":["1164:4179:10535:10759"]},"path":["10759"],"owner":"44499","recid":"214091","title":["音声認識のデータ拡張のための合成音声の周波数スペクトログラム強調"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-11-24"},"_buckets":{"deposit":"5a029a4e-648e-4d6b-935f-febeee9e9c2c"},"_deposit":{"id":"214091","pid":{"type":"depid","value":"214091","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"音声認識のデータ拡張のための合成音声の周波数スペクトログラム強調","author_link":["548600","548601"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"音声認識のデータ拡張のための合成音声の周波数スペクトログラム強調"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"データ拡張・ラベリング","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-11-24","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"京都大学情報学研究科"},{"subitem_text_value":"京都大学情報学研究科"}]},"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":"jpn"}]},"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/214091/files/IPSJ-NL21251028.pdf","label":"IPSJ-NL21251028.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-24"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL21251028.pdf","filesize":[{"value":"2.4 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":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"5412d264-48b6-4f33-b9a6-79e8b2c7916b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"上乃, 聖"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"河原, 達也"}],"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":"End-to-End 音声認識が高い精度を達成しつつあるが，大量のデータを必要とする．その問題の解決のために音声合成を用いて音声認識の訓練データを生成することを検討してきた．音声合成においては，通常テキストから対数メルフィルタバンクを作る text-to-mel ネットワークを用いた後に，メルスペクトログラムを音声波形に変換するボコーダを用いて，音声波形を生成する．それを再びメルスペクトログラムに変換し，音声認識の訓練データとして用いる．ボコーダには合成音声と自然音声の差異を埋める効果があるが，この波形生成に非常に時間がかかるという問題がある．そこで本研究ではボコーダを用いずに周波数スペクトログラム上で直接強調を行うネットワークを提案する．提案手法では，生成されたメルスペクトログラムだけでなく，音声合成のタスクで利用可能な音素情報も用いる．評価実験から，提案手法がボコーダを用いるよりも少ない処理時間で拡張の効果が高いことを示し，また，音素情報の利用が改善に重要であることを示した．","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":"2021-11-24","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"28","bibliographicVolumeNumber":"2021-NL-251"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":214091,"links":{}}