{"id":2331,"date":"2025-01-14T20:50:46","date_gmt":"2025-01-14T12:50:46","guid":{"rendered":"https:\/\/www.15zhi.net\/blog\/?p=2331"},"modified":"2025-01-14T20:50:46","modified_gmt":"2025-01-14T12:50:46","slug":"202501%e8%ae%ba%e6%96%87%e7%a0%94%e8%af%bb-prosodyfm-unsupervised-phrasing-and-intonation-control-for-intelligible-speech-synthesis","status":"publish","type":"post","link":"https:\/\/www.15zhi.net\/blog\/202501%e8%ae%ba%e6%96%87%e7%a0%94%e8%af%bb-prosodyfm-unsupervised-phrasing-and-intonation-control-for-intelligible-speech-synthesis\/","title":{"rendered":"202501\u8bba\u6587\u7814\u8bfb-ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis"},"content":{"rendered":"\n<p>\u4f5c\u8005\uff1aHe Xiangheng\u7b49<\/p>\n\n\n\n<p>\u5355\u4f4d\uff1aImperial College London<\/p>\n\n\n\n<p>\u6765\u6e90\uff1aAAAI 2025<\/p>\n\n\n\n<p class=\"has-x-large-font-size\">\u4e00\u3001\u4e3b\u8981\u5185\u5bb9<\/p>\n\n\n\n<p>\u97f5\u5f8b\u5bf9\u8bed\u97f3\u53ef\u7406\u89e3\u6027\u81f3\u5173\u91cd\u8981\uff0c\u76ee\u524d\u6a21\u578b\u5728\u5212\u5206\u505c\u987f\u548c\u8bed\u8c03\u65b9\u9762\u5b58\u5728\u4e0d\u8db3\u3002ProsodyFM\u5f15\u5165\u505c\u987f\u7f16\u7801\u5668\u548c\u8bed\u8c03\u7f16\u7801\u5668\uff0c\u6709\u6548\u6539\u5584\u97f5\u5f8b\u7684\u505c\u987f\u548c\u8bed\u8c03\u65b9\u9762\uff0c\u5e76\u7ad9\u5c55\u73b0\u51fa\u5353\u8d8a\u7684\u6cdb\u5316\u80fd\u529b\u3002<\/p>\n\n\n\n<p class=\"has-x-large-font-size\">\u4e8c\u3001\u8bba\u6587\u8d21\u732e<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u63d0\u51faProsodyFM\uff0c\u80fd\u591f\u5408\u6210\u81ea\u7136\u505c\u987f\u548c\u8bed\u8c03\u7684\u8bed\u97f3\u3002<\/li>\n\n\n\n<li>\u4e3a\u505c\u987f\u6807\u7b7e\u548c\u8bed\u8c03\u5efa\u6a21\u63d0\u4f9b\u65b0\u7684\u6709\u6548\u7684\u89e3\u51b3\u65b9\u6848\u3002<\/li>\n\n\n\n<li>\u53d1\u5e03\u6f14\u793a\u3001\u4ee3\u7801\u548c\u6a21\u578b\u6743\u91cd\u4fc3\u8fdb\u8fdb\u4e00\u6b65\u7814\u7a76\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"has-x-large-font-size\">\u4e09\u3001\u65b9\u6cd5<\/p>\n\n\n\n<p>ProsodyFM\u65e8\u5728\u4ece\u53c2\u8003\u8bed\u97f3\u4e2d\u63d0\u53d6\u505c\u987f\u548c\u8bed\u8c03\u6a21\u5f0f\uff0c\u8c03\u6574\u8fd9\u4e9b\u6a21\u5f0f\u5e76\u5339\u914d\u76ee\u6807\u6587\u672c\uff0c\u4f7f\u7528\u6700\u4f18\u4f20\u8f93\u6761\u4ef6\u6d41\u5339\u914dOT-CFM\u8fdb\u884c\u8bad\u7ec3\u3002ProsodyFM\u4ece\u539f\u59cb\u6587\u672c\u4e2d\u9884\u6d4bmel\u8c31\u56fe\uff0c\u4f7f\u7528HifiGAN\u58f0\u7801\u5668\u8f6c\u6362\u4e3a\u6ce2\u5f62\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"298\" src=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-72-1024x298.png\" alt=\"\" class=\"wp-image-2338\" srcset=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-72-1024x298.png 1024w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-72-300x87.png 300w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-72-768x223.png 768w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-72.png 1187w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"614\" height=\"417\" src=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-73.png\" alt=\"\" class=\"wp-image-2339\" srcset=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-73.png 614w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-73-300x204.png 300w\" sizes=\"auto, (max-width: 614px) 100vw, 614px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"569\" height=\"435\" src=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-74.png\" alt=\"\" class=\"wp-image-2340\" srcset=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-74.png 569w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-74-300x229.png 300w\" sizes=\"auto, (max-width: 569px) 100vw, 569px\" \/><\/figure>\n\n\n\n<p class=\"has-x-large-font-size\">\u56db\u3001\u7ed3\u679c<\/p>\n\n\n\n<p>\u6570\u636e\u96c6\uff1aLibriTTS<\/p>\n\n\n\n<p>\u5ba2\u89c2\u8bc4\u4ef7\u6307\u6807\uff1aRMSE<sub>F0<\/sub>\u5bf9\u6570\u5c3a\u5ea6F0\u5747\u65b9\u6839\u8bef\u5dee\uff0cF1<sub>break<\/sub>\u4e2d\u65ad\u5206\u7c7bF1\u5206\u6570\uff0cWER\u8bcd\u9519\u7387\u3002<\/p>\n\n\n\n<p>\u4e3b\u89c2\u8bc4\u4ef7\u6307\u6807\uff1aMOS\u5e73\u5747\u610f\u89c1\u5f97\u5206<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"427\" height=\"217\" src=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-75.png\" alt=\"\" class=\"wp-image-2342\" srcset=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-75.png 427w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-75-300x152.png 300w\" sizes=\"auto, (max-width: 427px) 100vw, 427px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"554\" height=\"162\" src=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-76.png\" alt=\"\" class=\"wp-image-2343\" srcset=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-76.png 554w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-76-300x88.png 300w\" sizes=\"auto, (max-width: 554px) 100vw, 554px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"419\" height=\"222\" src=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-77.png\" alt=\"\" class=\"wp-image-2344\" srcset=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-77.png 419w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-77-300x159.png 300w\" sizes=\"auto, (max-width: 419px) 100vw, 419px\" \/><\/figure>\n\n\n\n<p>\u6d88\u878d\u5b9e\u9a8c\uff1a<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"417\" height=\"188\" src=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-78.png\" alt=\"\" class=\"wp-image-2345\" srcset=\"https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-78.png 417w, https:\/\/www.15zhi.net\/blog\/wp-content\/uploads\/2025\/01\/image-78-300x135.png 300w\" sizes=\"auto, (max-width: 417px) 100vw, 417px\" \/><\/figure>\n\n\n\n<p class=\"has-x-large-font-size\">\u4e94\u3001\u7ed3\u8bba<\/p>\n\n\n\n<p>\u63d0\u51fa\u65b0\u7684\u97f5\u5f8b\u611f\u77e5TTS\u6a21\u578b\uff0c\u5728\u4e0d\u9700\u8981\u97f5\u5f8b\u6807\u7b7e\u7684\u60c5\u51b5\u4e0b\u589e\u5f3a\u505c\u987f\u548c\u8bed\u8c03\uff0c\u5b9e\u73b0\u4e86\u5bf9\u505c\u987f\u548c\u8bed\u8c03\u7684\u5f3a\u5927\u3001\u7cbe\u786e\u548c\u7ec6\u7c92\u5ea6\u7684\u63a7\u5236\u3002<\/p>\n\n\n\n<p class=\"has-x-large-font-size\">\u516d\u3001\u5bf9\u9f50\u601d\u8003<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u5728\u5507\u8bed\u5230\u8bed\u97f3\u5408\u6210\u4efb\u52a1\u4e2d\uff0c\u89c6\u89c9\u4fe1\u606f\u548c\u8bed\u97f3\u7684\u505c\u987f\u4e4b\u95f4\u5b58\u5728\u5929\u7136\u7684\u5bf9\u5e94\u5173\u7cfb\uff0c\u52a0\u5165\u8bed\u97f3\u505c\u987f\u53ef\u4ee5\u6539\u5584\u5408\u6210\u8bed\u97f3\u7684\u97f5\u5f8b\u3002<\/li>\n\n\n\n<li>\u5bf9\u57fa\u9891\u7684\u5904\u7406\u6709\u53c2\u8003\u4ef7\u503c<\/li>\n<\/ul>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4f5c\u8005\uff1aHe Xiangheng\u7b49 \u5355\u4f4d\uff1aImperial College London \u6765\u6e90\uff1aAAAI 202 [&hellip;]<\/p>\n","protected":false},"author":10,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-2331","post","type-post","status-publish","format-standard","hentry","category-events"],"_links":{"self":[{"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/posts\/2331","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/comments?post=2331"}],"version-history":[{"count":7,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/posts\/2331\/revisions"}],"predecessor-version":[{"id":2349,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/posts\/2331\/revisions\/2349"}],"wp:attachment":[{"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/media?parent=2331"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/categories?post=2331"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/tags?post=2331"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}