{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00057459","sets":["1164:5159:5210:5211"]},"path":["5211"],"owner":"1","recid":"57459","title":["環境音モデルとHMM合成を用いた音声区間検出の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2000-12-21"},"_buckets":{"deposit":"685b67f9-2a71-4a7f-8e17-ee02e55e3f84"},"_deposit":{"id":"57459","pid":{"type":"depid","value":"57459","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"環境音モデルとHMM合成を用いた音声区間検出の検討","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"環境音モデルとHMM合成を用いた音声区間検出の検討"},{"subitem_title":"Voice Activity Detection Using Non - speech Models and HMM Composition","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2000-12-21","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大学大学院理工学研究科"},{"subitem_text_value":"筑波大学電子・情報工学系"},{"subitem_text_value":"電子技術総合研究所"},{"subitem_text_value":"筑波大学電子・情報工学系"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Master's Program in Science and Engineering, University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Institute of Information Sciences and Electronics, University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Electrotechnical Laboratory","subitem_text_language":"en"},{"subitem_text_value":"Institute of Information Sciences and Electronics, University of Tsukuba","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/57459/files/IPSJ-SLP00034010.pdf"},"date":[{"dateType":"Available","dateValue":"2002-12-21"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-SLP00034010.pdf","filesize":[{"value":"617.4 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":"856078e2-a367-40ba-851a-87b5b051c7d3","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2000 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"渡部, 生聖"},{"creatorName":"山田, 武志"},{"creatorName":"浅野, 太"},{"creatorName":"北脇, 信彦"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Narimasa, Watanabe","creatorNameLang":"en"},{"creatorName":"Takeshi, Yamada","creatorNameLang":"en"},{"creatorName":"Futoshi, Asano","creatorNameLang":"en"},{"creatorName":"Nobuhiko, Kitawaki","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本稿では，音声と環境音が重畳している場合にも頑健かつ効率的な音声区間検出を行うために，環境音モデルとHMM合成を用いる方法を提案する．提案法では，まず音声と環境音のモデルを用いてビタビアライメントを求め，音声に重畳している環境音を予測する．そして，音声と予測した環境音の重畳モデルをHMM合成により作成し，この重畳モデルを加えて再度ビタビアライメントを求める．その結果，音声と環境音が重畳している区間，重畳している環境音とそのSN比を検出できる．9通りの環境音を音声に重畳し，音声区間検出の実験を行った結果，提案法の音声区間検出率は従来法と比べて数％から最大で40％程度高いことが明らかとなった．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper proposes a new voice activity detection (VAD) method using non-speech models and HMM composition. The proposed method predicts a non-speech sound that overlaps with speech by a Viterbi algorithm with a speech model and non-speech models. Then, a Viterbi algorithm with composed models of the speech model and the predicted non-speech sound  models is applied again. As a result, the overlap segments are detected. Furthermore, the non-speech sound that overlaps with speech and its SNR are identified. To evaluate the performance of the proposed method, preliminary experiments are conducted. These results showed that the VAD accuracy of the proposed method is improved by a maximum of 40% compared to that of the conventional method.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"60","bibliographic_titles":[{"bibliographic_title":"情報処理学会研究報告音声言語情報処理（SLP）"}],"bibliographicPageStart":"55","bibliographicIssueDates":{"bibliographicIssueDate":"2000-12-21","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"119(2000-SLP-034)","bibliographicVolumeNumber":"2000"}]},"relation_version_is_last":true,"weko_creator_id":"1"},"id":57459,"updated":"2025-01-22T04:28:56.376082+00:00","links":{},"created":"2025-01-18T23:20:39.491431+00:00"}