WEKO3
アイテム
{"_buckets": {"deposit": "0778897f-3ed4-4a10-af0a-679b585d5de1"}, "_deposit": {"created_by": 4, "id": "4713", "owners": [4], "pid": {"revision_id": 0, "type": "depid", "value": "4713"}, "status": "published"}, "_oai": {"id": "oai:naist.repo.nii.ac.jp:00004713", "sets": ["36"]}, "author_link": ["12345", "12346", "12347", "12348", "12349"], "item_1698715929687": {"attribute_name": "会議情報", "attribute_value_mlt": [{"subitem_conference_country": "USA", "subitem_conference_date": {"subitem_conference_date_language": "en", "subitem_conference_period": "September 17-21, 2006"}, "subitem_conference_names": [{"subitem_conference_name": "INTERSPEECH2006: the 9th International Conference on Spoken Language Processing (ICSLP)", "subitem_conference_name_language": "en"}], "subitem_conference_places": [{"subitem_conference_place": "Pittsburgh Pennsylvania", "subitem_conference_place_language": "en"}]}]}, "item_9_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2006-09", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "2281", "bibliographicPageStart": "2278"}]}, "item_9_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "This paper describes the voice conversion based on the Mixtures of Factor Analyzers (MFA) which can provide an efficient modeling with a limited amount of training data. As a typical spectral conversion method, a mapping algorithm based on the Gaussian Mixture Model (GMM) has been proposed. In this method two kinds of covariance matrix structures are often used : the diagonal and full covariance matrices. GMM with diagonal covariance matrices requires a large number of mixture components for accurately estimating spectral features. On the other hand, GMM with full covariance matrices needs sufficient training data to estimate model parameters. In order to cope with these problems, we apply MFA to voice conversion. MFA can be regarded as intermediate model between GMM with diagonal covariance and with full covariance. Experimental results show that MFA can improve the conversion accuracy compared with the conventional GMM.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_9_rights_14": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "Copyright 2006 ISCA", "subitem_rights_language": "en"}]}, "item_9_text_21": {"attribute_name": "NAIST ID", "attribute_value_mlt": [{"subitem_text_value": "73292716"}]}, "item_9_text_22": {"attribute_name": "artnum", "attribute_value_mlt": [{"subitem_text_value": "2076"}]}, "item_9_version_type_16": {"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_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "open access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_abf2"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Uto, Yosuke", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "12345", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Nankaku, Yoshihiko", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "12346", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Toda, Tomoki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "12347", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Lee, Akinobu", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "12348", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Tokuda, Keiichi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "12349", "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": "2023-03-02"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "INTERSPEECH_2006_2278.pdf", "filesize": [{"value": "622.7 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_note", "mimetype": "application/pdf", "size": 622700.0, "url": {"label": "fulltext", "objectType": "fulltext", "url": "https://naist.repo.nii.ac.jp/record/4713/files/INTERSPEECH_2006_2278.pdf"}, "version_id": "20df2056-a91d-49c2-bac2-651cc2bd753c"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "voice conversion", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "GMM (Gaussian Mixture Model)", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "MFA (Mixtures of Factor Analyzers)", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}]}, "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": "conference paper", "resourceuri": "http://purl.org/coar/resource_type/c_5794"}]}, "item_title": "Voice Conversion Based on Mixtures of Factor Analyzers", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Voice Conversion Based on Mixtures of Factor Analyzers", "subitem_title_language": "en"}]}, "item_type_id": "9", "owner": "4", "path": ["36"], "permalink_uri": "http://hdl.handle.net/10061/8145", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2012-08-22"}, "publish_date": "2012-08-22", "publish_status": "0", "recid": "4713", "relation": {}, "relation_version_is_last": true, "title": ["Voice Conversion Based on Mixtures of Factor Analyzers"], "weko_shared_id": -1}
Voice Conversion Based on Mixtures of Factor Analyzers
http://hdl.handle.net/10061/8145
http://hdl.handle.net/10061/81452ff70c57-2ffb-4bfa-bf55-db0cd6962422
名前 / ファイル | ライセンス | アクション |
---|---|---|
fulltext (622.7 kB)
|
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2012-08-22 | |||||
タイトル | ||||||
タイトル | Voice Conversion Based on Mixtures of Factor Analyzers | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | voice conversion | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | GMM (Gaussian Mixture Model) | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | MFA (Mixtures of Factor Analyzers) | |||||
資源タイプ | ||||||
資源タイプ | conference paper | |||||
アクセス権 | ||||||
アクセス権 | open access | |||||
著者 |
Uto, Yosuke
× Uto, Yosuke× Nankaku, Yoshihiko× Toda, Tomoki× Lee, Akinobu× Tokuda, Keiichi |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | This paper describes the voice conversion based on the Mixtures of Factor Analyzers (MFA) which can provide an efficient modeling with a limited amount of training data. As a typical spectral conversion method, a mapping algorithm based on the Gaussian Mixture Model (GMM) has been proposed. In this method two kinds of covariance matrix structures are often used : the diagonal and full covariance matrices. GMM with diagonal covariance matrices requires a large number of mixture components for accurately estimating spectral features. On the other hand, GMM with full covariance matrices needs sufficient training data to estimate model parameters. In order to cope with these problems, we apply MFA to voice conversion. MFA can be regarded as intermediate model between GMM with diagonal covariance and with full covariance. Experimental results show that MFA can improve the conversion accuracy compared with the conventional GMM. | |||||
書誌情報 |
p. 2278-2281, 発行日 2006-09 |
|||||
artnum | ||||||
2076 | ||||||
会議情報 | ||||||
会議名 | INTERSPEECH2006: the 9th International Conference on Spoken Language Processing (ICSLP) | |||||
開催期間 | September 17-21, 2006 | |||||
開催地 | Pittsburgh Pennsylvania | |||||
開催国 | USA | |||||
権利 | ||||||
権利情報 | Copyright 2006 ISCA | |||||
著者版フラグ | ||||||
出版タイプ | VoR |