{"created":"2025-01-18T23:39:52.666382+00:00","updated":"2025-01-20T06:49:30.561779+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00090265","sets":["581:7002:7080"]},"path":["7080"],"owner":"11","recid":"90265","title":["Collecting Colloquial and Spontaneous-like Sentences from Web Resources for Constructing Chinese Language Models of Speech Recognition"],"pubdate":{"attribute_name":"公開日","attribute_value":"2013-02-15"},"_buckets":{"deposit":"1422809f-448b-4842-9120-163f385c75b0"},"_deposit":{"id":"90265","pid":{"type":"depid","value":"90265","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"Collecting Colloquial and Spontaneous-like Sentences from Web Resources for Constructing Chinese Language Models of Speech Recognition","author_link":["358211","358213","358214","358216","358217","358215","358218","358212"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Collecting Colloquial and Spontaneous-like Sentences from Web Resources for Constructing Chinese Language Models of Speech Recognition"},{"subitem_title":"Collecting Colloquial and Spontaneous-like Sentences from Web Resources for Constructing Chinese Language Models of Speech Recognition","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[特集：音声ドキュメント処理] spontaneous text collection, the Web data, Chinese language model, automatic speech recognition","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2013-02-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"National Institute of Information and Communications Technology (NICT)"},{"subitem_text_value":"National Institute of Information and Communications Technology (NICT)"},{"subitem_text_value":"National Institute of Information and Communications Technology (NICT)"},{"subitem_text_value":"National Institute of Information and Communications Technology (NICT)"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Information and Communications Technology (NICT)","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Information and Communications Technology (NICT)","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Information and Communications Technology (NICT)","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Information and Communications Technology (NICT)","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"publish_status":"0","weko_shared_id":11,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/90265/files/IPSJ-JNL5402005.pdf","label":"IPSJ-JNL5402005"},"date":[{"dateType":"Available","dateValue":"2015-02-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL5402005.pdf","filesize":[{"value":"1.2 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"2deca15a-c374-42b9-bf08-4bd705dc21e6","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2013 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Xinhui, Hu"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shigeki, Matsuda"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Chori, Hori"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hideki, Kashioka"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Xinhui, Hu","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shigeki, Matsuda","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Chori, Hori","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hideki, Kashioka","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"In this paper, we present our work on collecting training texts from the Web for constructing language models in colloquial and spontaneous Chinese automatic speech recognition systems. The selection involves two steps: first, web texts are selected using a perplexity-based approach in which the style-related words are strengthened by omitting infrequent topic words. Second, the selected texts are then clustered based on non-noun part-of-speech words and optimal clusters are chosen by referring to a set of spontaneous seed sentences. With the proposed method, we selected over 3.80 M sentences. By qualitative analysis on the selected results, the colloquial and spontaneous-speech like texts are effectively selected. The effectiveness of the selection is also quantitatively verified by the speech recognition experiments. Using the language model interpolated with the one trained by these selected sentences and a baseline model, speech recognition evaluations were conducted on an open domain colloquial and spontaneous test set. We effectively reduced the character error rate 4.0% over the baseline model meanwhile the word coverage was also greatly increased. We also verified that the proposed method is superior to a conventional perplexity-based approach with a difference of 1.57% in character error rate.\n\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.21(2013) No.2 (online)\nDOI http://dx.doi.org/10.2197/ipsjjip.21.168\n------------------------------","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this paper, we present our work on collecting training texts from the Web for constructing language models in colloquial and spontaneous Chinese automatic speech recognition systems. The selection involves two steps: first, web texts are selected using a perplexity-based approach in which the style-related words are strengthened by omitting infrequent topic words. Second, the selected texts are then clustered based on non-noun part-of-speech words and optimal clusters are chosen by referring to a set of spontaneous seed sentences. With the proposed method, we selected over 3.80 M sentences. By qualitative analysis on the selected results, the colloquial and spontaneous-speech like texts are effectively selected. The effectiveness of the selection is also quantitatively verified by the speech recognition experiments. Using the language model interpolated with the one trained by these selected sentences and a baseline model, speech recognition evaluations were conducted on an open domain colloquial and spontaneous test set. We effectively reduced the character error rate 4.0% over the baseline model meanwhile the word coverage was also greatly increased. We also verified that the proposed method is superior to a conventional perplexity-based approach with a difference of 1.57% in character error rate.\n\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.21(2013) No.2 (online)\nDOI http://dx.doi.org/10.2197/ipsjjip.21.168\n------------------------------","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicIssueDates":{"bibliographicIssueDate":"2013-02-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"54"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":90265,"links":{}}