{"id":865,"date":"2021-10-18T04:30:00","date_gmt":"2021-10-17T19:30:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=865"},"modified":"2021-10-18T04:30:00","modified_gmt":"2021-10-17T19:30:00","slug":"speecht5-%e9%9f%b3%e5%a3%b0%e6%83%85%e5%a0%b1%e5%90%91%e3%81%91t5","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=865","title":{"rendered":"SpeechT5: \u97f3\u58f0\u60c5\u5831\u5411\u3051T5"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><strong>SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing&nbsp;<\/strong>[77.5]<br>\u672c\u7a3f\u3067\u306f,\u81ea\u5df1\u6559\u5e2b\u4ed8\u304d\u97f3\u58f0\/\u30c6\u30ad\u30b9\u30c8\u8868\u73fe\u5b66\u7fd2\u306e\u305f\u3081\u306e\u30a8\u30f3\u30b3\u30fc\u30c0\u30fb\u30c7\u30b3\u30fc\u30c0\u4e8b\u524d\u5b66\u7fd2\u3092\u63a2\u7d22\u3059\u308b\u7d71\u4e00\u30e2\u30fc\u30c0\u30eb\u306aSpeechT5\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u63d0\u6848\u3059\u308b\u3002 SpeechT5\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306f\u5171\u6709\u30a8\u30f3\u30b3\u30fc\u30c0\u30c7\u30b3\u30fc\u30c0\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u30686\u3064\u306e\u30e2\u30fc\u30c0\u30eb\u56fa\u6709(\u97f3\u58f0\/\u30c6\u30ad\u30b9\u30c8)\u30d7\u30ec\/\u30dd\u30b9\u30c8\u30cd\u30c3\u30c8\u3067\u69cb\u6210\u3055\u308c\u3066\u3044\u308b\u3002 \u30c6\u30ad\u30b9\u30c8\u60c5\u5831\u3068\u97f3\u58f0\u60c5\u5831\u3092\u7d71\u4e00\u7684\u306a\u610f\u5473\u7a7a\u9593\u306b\u6574\u5408\u3055\u305b\u308b\u305f\u3081,\u30c6\u30ad\u30b9\u30c8\u3068\u30c6\u30ad\u30b9\u30c8\u3092\u30e9\u30f3\u30c0\u30e0\u306b\u6df7\u5408\u3057\u305f\u30af\u30ed\u30b9\u30e2\u30fc\u30c0\u30eb\u30d9\u30af\u30c8\u30eb\u91cf\u5b50\u5316\u6cd5\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2110.07205v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2110.07205v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 14 Oct 2021 07:59:27 GMT)<ul><li>T5\u306b\u4f3c\u305f\u4e8b\u524d\u5b66\u7fd2\u30e2\u30c7\u30eb\u3092\u97f3\u58f0\u5411\u3051\u306b\u69cb\u7bc9\u3001ASR\u3001TTS\u3001VC\u3001SID\u306a\u3069\u8907\u6570\u306e\u30bf\u30b9\u30af\u3067\u52b9\u679c\u3092\u78ba\u8a8d\u3068\u306e\u3053\u3068\u3002TextlessNLP\u306e\u3088\u3046\u306a\u6d41\u308c\u306b\u5411\u3051\u305f\u4e00\u6b69\u306b\u306a\u308b\u306e\u3060\u308d\u3046\u304b\u3002<ul><li>ASR: Automatic Speech Recognition<\/li><li>TTS: Text-To-Speech<\/li><li>VC: Voice Conversion<\/li><li>SID: Speaker IDenti\ufb01cation<\/li><\/ul><\/li><\/ul><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing&nbsp;[77.5]\u672c\u7a3f\u3067\u306f,\u81ea\u5df1\u6559\u5e2b\u4ed8\u304d\u97f3\u58f0\/\u30c6 &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=865\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;SpeechT5: \u97f3\u58f0\u60c5\u5831\u5411\u3051T5&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[372,403,567,668],"class_list":["post-865","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-speecht5","tag-textlessnlp","tag-567","tag-668"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/865","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=865"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/865\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=865"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=865"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=865"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}