WEKO3
アイテム
{"_buckets": {"deposit": "f2d6b5e2-7032-4416-b343-031efea52c77"}, "_deposit": {"created_by": 3, "id": "5233", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "5233"}, "status": "published"}, "_oai": {"id": "oai:nitech.repo.nii.ac.jp:00005233", "sets": ["31"]}, "author_link": ["8555", "3028", "464", "17805", "17808", "8864"], "item_10001_biblio_info_28": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2005-03-01", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "3", "bibliographicPageEnd": "417", "bibliographicPageStart": "410", "bibliographicVolumeNumber": "E88-D", "bibliographic_titles": [{"bibliographic_title": "IEICE transactions on information and systems"}]}]}, "item_10001_description_36": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "This paper describes continuous speech recognition incorporating the additional complement information, e.g., voice characteristics, speaking styles, linguistic information and noise environment, into HMM-based acoustic modeling. In speech recognition systems, context-dependent HMMs, i.e., triphone, and the tree-based context clustering have commonly been used. Several attempts to utilize not only phonetic contexts, but additional complement information based on context (factor) dependent HMMs have been made in recent years. However, when the additional factors for testing data are unobserved, methods for obtaining factor labels is required before decoding. In this paper, we propose a model integration technique based on general factor dependent HMMs for decoding. The integrated HMMs can be used by a conventional decoder as standard triphone HMMs with Gaussian mixture densities. Moreover, by using the results of context clustering, the proposed method can determine an optimal number of mixture components for each state dependently of the degree of influence from additional factors. Phoneme recognition experiments using voice characteristic labels show significant improvements with a small number of model parameters, and a 19.3% error reduction was obtained in noise environment experiments.", "subitem_description_type": "Other"}]}, "item_10001_description_38": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_description": "application/pdf", "subitem_description_type": "Other"}]}, "item_10001_full_name_27": {"attribute_name": "著者別名", "attribute_value_mlt": [{"affiliations": [{"affiliationNames": [{"affiliationName": "", "lang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "", "nameIdentifierScheme": "ISNI", "nameIdentifierURI": "http://www.isni.org/isni/"}]}], "familyNames": [{"familyName": "Nankaku", "familyNameLang": "en"}, {"familyName": "南角", "familyNameLang": "ja"}, {"familyName": "ナンカク", "familyNameLang": "ja-Kana"}], "givenNames": [{"givenName": "Yoshihiko", "givenNameLang": "en"}, {"givenName": "吉彦", "givenNameLang": "ja"}, {"givenName": "ヨシヒコ", "givenNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "8555", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "1000080397497", "nameIdentifierScheme": "NRID", "nameIdentifierURI": "http://rns.nii.ac.jp/nr/1000080397497"}], "names": [{"name": "Nankaku, Yoshihiko", "nameLang": "en"}, {"name": "南角, 吉彦", "nameLang": "ja"}, {"name": "ナンカク, ヨシヒコ", "nameLang": "ja-Kana"}]}, {"affiliations": [{"affiliationNames": [{"affiliationName": "", "lang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "", "nameIdentifierScheme": "ISNI", "nameIdentifierURI": "http://www.isni.org/isni/"}]}], "familyNames": [{"familyName": "Tokuda", "familyNameLang": "en"}, {"familyName": "徳田", "familyNameLang": "ja"}, {"familyName": "トクダ", "familyNameLang": "ja-Kana"}], "givenNames": [{"givenName": "Keiichi", "givenNameLang": "en"}, {"givenName": "恵一", "givenNameLang": "ja"}, {"givenName": "ケイイチ", "givenNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "464", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "1000020217483", "nameIdentifierScheme": "NRID", "nameIdentifierURI": "http://rns.nii.ac.jp/nr/1000020217483"}], "names": [{"name": "Tokuda, Keiichi", "nameLang": "en"}, {"name": "徳田, 恵一", "nameLang": "ja"}, {"name": "トクダ, ケイイチ", "nameLang": "ja-Kana"}]}, {"nameIdentifiers": [{"nameIdentifier": "3028", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "北村, 正"}]}]}, "item_10001_publisher_29": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Institute of Electronics, Information and Communication Engineers"}]}, "item_10001_source_id_30": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "09168532", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_source_id_32": {"attribute_name": "書誌レコードID(NCID)", "attribute_value_mlt": [{"subitem_source_identifier": "AA10826272", "subitem_source_identifier_type": "NCID"}]}, "item_10001_version_type_33": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Suzuki, Hiroyuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "17805", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Zen, Heiga", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "8864", "nameIdentifierScheme": "WEKO"}]}, {"creatorAffiliations": [{"affiliationNameIdentifiers": [{"affiliationNameIdentifier": "", "affiliationNameIdentifierScheme": "ISNI", "affiliationNameIdentifierURI": "http://www.isni.org/isni/"}], "affiliationNames": [{"affiliationName": "", "affiliationNameLang": "ja"}]}], "creatorNames": [{"creatorName": "Nankaku, Yoshihiko", "creatorNameLang": "en"}, {"creatorName": "南角, 吉彦", "creatorNameLang": "ja"}, {"creatorName": "ナンカク, ヨシヒコ", "creatorNameLang": "ja-Kana"}], "familyNames": [{"familyName": "Nankaku", "familyNameLang": "en"}, {"familyName": "南角", "familyNameLang": "ja"}, {"familyName": "ナンカク", "familyNameLang": "ja-Kana"}], "givenNames": [{"givenName": "Yoshihiko", "givenNameLang": "en"}, {"givenName": "吉彦", "givenNameLang": "ja"}, {"givenName": "ヨシヒコ", "givenNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "8555", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "1000080397497", "nameIdentifierScheme": "NRID", "nameIdentifierURI": "http://rns.nii.ac.jp/nr/1000080397497"}]}, {"creatorNames": [{"creatorName": "Miyajima, Chiyomi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "17808", "nameIdentifierScheme": "WEKO"}]}, {"creatorAffiliations": [{"affiliationNameIdentifiers": [{"affiliationNameIdentifier": "", "affiliationNameIdentifierScheme": "ISNI", "affiliationNameIdentifierURI": "http://www.isni.org/isni/"}], "affiliationNames": [{"affiliationName": "", "affiliationNameLang": "ja"}]}], "creatorNames": [{"creatorName": "Tokuda, Keiichi", "creatorNameLang": "en"}, {"creatorName": "徳田, 恵一", "creatorNameLang": "ja"}, {"creatorName": "トクダ, ケイイチ", "creatorNameLang": "ja-Kana"}], "familyNames": [{"familyName": "Tokuda", "familyNameLang": "en"}, {"familyName": "徳田", "familyNameLang": "ja"}, {"familyName": "トクダ", "familyNameLang": "ja-Kana"}], "givenNames": [{"givenName": "Keiichi", "givenNameLang": "en"}, {"givenName": "恵一", "givenNameLang": "ja"}, {"givenName": "ケイイチ", "givenNameLang": "ja-Kana"}], "nameIdentifiers": [{"nameIdentifier": "464", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "1000020217483", "nameIdentifierScheme": "NRID", "nameIdentifierURI": "http://rns.nii.ac.jp/nr/1000020217483"}]}, {"creatorNames": [{"creatorName": "Kitamura, Tadashi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "3028", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2017-01-25"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "E88-D_410.pdf", "filesize": [{"value": "496.9 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "Copyright(c)2005 IEICE http://search.ieice.org/index.html", "licensetype": "license_free", "mimetype": "application/pdf", "size": 496900.0, "url": {"label": "本文_fulltext", "url": "https://nitech.repo.nii.ac.jp/record/5233/files/E88-D_410.pdf"}, "version_id": "3300d995-7d0a-46eb-a6e2-8eeebf631bb6"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Continuous Speech Recognition Based on General Factor Dependent Acoustic Models", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Continuous Speech Recognition Based on General Factor Dependent Acoustic Models", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "3", "path": ["31"], "permalink_uri": "https://nitech.repo.nii.ac.jp/records/5233", "pubdate": {"attribute_name": "公開日", "attribute_value": "2012-11-07"}, "publish_date": "2012-11-07", "publish_status": "0", "recid": "5233", "relation": {}, "relation_version_is_last": true, "title": ["Continuous Speech Recognition Based on General Factor Dependent Acoustic Models"], "weko_shared_id": 3}
Continuous Speech Recognition Based on General Factor Dependent Acoustic Models
https://nitech.repo.nii.ac.jp/records/5233
https://nitech.repo.nii.ac.jp/records/5233fadc1488-b9de-4bca-90d9-50d7a9b8afd0
名前 / ファイル | ライセンス | アクション |
---|---|---|
本文_fulltext (496.9 kB)
|
Copyright(c)2005 IEICE http://search.ieice.org/index.html
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2012-11-07 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Continuous Speech Recognition Based on General Factor Dependent Acoustic Models | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | journal article | |||||
著者 |
Suzuki, Hiroyuki
× Suzuki, Hiroyuki× Zen, Heiga× 南角, 吉彦× Miyajima, Chiyomi× 徳田, 恵一× Kitamura, Tadashi |
|||||
著者別名 | ||||||
姓名 | Nankaku, Yoshihiko | |||||
言語 | en | |||||
姓名 | 南角, 吉彦 | |||||
言語 | ja | |||||
姓名 | ナンカク, ヨシヒコ | |||||
言語 | ja-Kana | |||||
著者別名 | ||||||
姓名 | Tokuda, Keiichi | |||||
言語 | en | |||||
姓名 | 徳田, 恵一 | |||||
言語 | ja | |||||
姓名 | トクダ, ケイイチ | |||||
言語 | ja-Kana | |||||
著者別名 | ||||||
姓名 | 北村, 正 | |||||
書誌情報 |
IEICE transactions on information and systems 巻 E88-D, 号 3, p. 410-417, 発行日 2005-03-01 |
|||||
出版者 | ||||||
出版者 | Institute of Electronics, Information and Communication Engineers | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 09168532 | |||||
書誌レコードID(NCID) | ||||||
収録物識別子タイプ | NCID | |||||
収録物識別子 | AA10826272 | |||||
著者版フラグ | ||||||
出版タイプ | VoR | |||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
内容記述 | ||||||
内容記述タイプ | Other | |||||
内容記述 | This paper describes continuous speech recognition incorporating the additional complement information, e.g., voice characteristics, speaking styles, linguistic information and noise environment, into HMM-based acoustic modeling. In speech recognition systems, context-dependent HMMs, i.e., triphone, and the tree-based context clustering have commonly been used. Several attempts to utilize not only phonetic contexts, but additional complement information based on context (factor) dependent HMMs have been made in recent years. However, when the additional factors for testing data are unobserved, methods for obtaining factor labels is required before decoding. In this paper, we propose a model integration technique based on general factor dependent HMMs for decoding. The integrated HMMs can be used by a conventional decoder as standard triphone HMMs with Gaussian mixture densities. Moreover, by using the results of context clustering, the proposed method can determine an optimal number of mixture components for each state dependently of the degree of influence from additional factors. Phoneme recognition experiments using voice characteristic labels show significant improvements with a small number of model parameters, and a 19.3% error reduction was obtained in noise environment experiments. | |||||
フォーマット | ||||||
内容記述タイプ | Other | |||||
内容記述 | application/pdf |