{"id":11217,"date":"2026-05-19T19:48:18","date_gmt":"2026-05-19T11:48:18","guid":{"rendered":"https:\/\/infernews.com\/blog\/yingmusic-singer\/"},"modified":"2026-08-19T19:51:08","modified_gmt":"2026-08-19T11:51:08","slug":"yingmusic-singer","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/yingmusic-singer\/","title":{"rendered":"YingMusic-Singer \u6539\u6b4c\u8a5e\u4e5f\u4e0d\u7528\u91cd\u5531"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/08\/pasted-0eba731f7280.jpg\" alt=\"pipeline\"><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">YingMusic-Singer \u662f\u4e00\u500b Zero-shot Singing Voice Synthesis (SVS) \u8207\u7de8\u8f2f\u6846\u67b6\uff0c\u76ee\u6a19\u662f\u89e3\u6c7a\u6b4c\u8072\u5408\u6210\u88e1\u6700\u9ebb\u7169\u7684\u5c0d\u9f4a\u548c\u6a19\u8a3b\u6210\u672c\u3002\u5b83\u628a\u300c\u7528\u53c3\u8003\u65cb\u5f8b\u751f\u6210\u65b0\u6b4c\u8a5e\u300d\u548c\u300c\u76f4\u63a5\u6539\u5beb\u65e2\u6709\u6b4c\u8072\u300d\u653e\u5728\u540c\u4e00\u5957\u6d41\u7a0b\u5167\uff0c\u5c0d\u8981\u505a\u5feb\u901f\u539f\u578b\u3001\u97f3\u6a02\u5167\u5bb9\u6539\u7a3f\u3001\u6216\u6279\u91cf\u88fd\u4f5c\u4e0d\u540c\u7248\u672c\u6b4c\u8072\u7684\u5718\u968a\u7279\u5225\u6709\u5438\u5f15\u529b\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5b83\u7684\u6838\u5fc3\u505a\u6cd5\u662f Annotation-free Melody Guidance\uff0c\u4e0d\u7528\u518d\u4f9d\u8cf4\u6602\u8cb4\u7684 phoneme-level alignment\uff0c\u4ea6\u4e0d\u9700\u8981\u4eba\u5de5\u88dc MIDI \u6a19\u8a3b\u3002\u4f7f\u7528\u6642\u53ef\u4ee5\u9935\u5165\u53c3\u8003\u97f3\u8a0a\uff0c\u8b93\u7cfb\u7d71\u81ea\u52d5\u62bd\u65cb\u5f8b\uff1b\u4ea6\u53ef\u4ee5\u76f4\u63a5\u8f38\u5165 MIDI\uff0c\u4ee4\u65cb\u5f8b\u4f86\u6e90\u66f4\u5f48\u6027\u3002\u4ee4\u5b83\u6bd4\u50b3\u7d71\u8981\u9010\u53e5\u5c0d\u9f4a\u7684\u505a\u6cd5\u8f15\u8eab\u5f88\u591a\uff0c\u4f46\u4e5f\u610f\u5473\u8457\u6210\u54c1\u8cea\u7d20\u6703\u66f4\u4f9d\u8cf4\u53c3\u8003\u65cb\u5f8b\u672c\u8eab\u662f\u5426\u6e05\u6670\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u652f\u63f4 zero-shot \u5408\u6210\u8207\u7de8\u8f2f\uff0c\u5169\u7a2e\u6d41\u7a0b\u653e\u5728\u540c\u4e00\u500b\u6846\u67b6\u5167<\/li>\n<li>\u53ef\u7531\u53c3\u8003\u97f3\u8a0a\u81ea\u52d5\u62bd\u65cb\u5f8b\uff0c\u4ea6\u53ef\u76f4\u63a5\u7528 MIDI<\/li>\n<li>\u4e0d\u9700\u8981\u91dd\u5c0d\u76ee\u6a19\u8072\u7dda\u518d\u505a\u5fae\u8abf<\/li>\n<li>beta \u7248\u5df2\u505c\u7528\uff0c\u73fe\u6642\u8981\u6539\u7528 beta \u5206\u652f<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u6280\u8853\u4e0a\uff0c\u5b83\u63a1\u7528 Diffusion Transformer (DiT) \u5f0f\u751f\u6210\u6a21\u578b\uff0c\u518d\u914d\u5408\u9810\u8a13\u7df4\u65cb\u5f8b\u62bd\u53d6\u6a21\u7d44\uff0c\u7531\u53c3\u8003\u97f3\u8a0a\u5c0e\u51fa MIDI \u8cc7\u8a0a\uff0c\u7136\u5f8c\u518d\u505a\u53d7\u63a7\u751f\u6210\u3002\u52a0\u5165 Flow-GRPO reinforcement learning \u53bb\u6539\u5584\u767c\u97f3\u6e05\u6670\u5ea6\u3001\u65cb\u5f8b\u6e96\u78ba\u5ea6\u548c\u97f3\u6a02\u6027\uff0c\u4f46\u73fe\u6709\u516c\u958b\u8cc7\u6599\u672a\u898b\u5b8c\u6574\u91cf\u5316\u8868\u683c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/giantailab.github.io\/YingMusic-Singer-demo\/\" rel=\"noopener noreferrer\"><strong>\u9805\u76ee\u4e3b\u9801<\/strong><\/a> \u00b7 <a href=\"https:\/\/github.com\/GiantAILab\/YingMusic-Singer\" rel=\"noopener noreferrer\"><strong>GitHub<\/strong><\/a> \u00b7 <a href=\"https:\/\/huggingface.co\/GiantAILab\/YingMusic-Singer\" rel=\"noopener noreferrer\"><strong>\u6a21\u578b<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4f60\u53ef\u4ee5\u628a\u5b83\u7406\u89e3\u6210\u4e00\u500b\u628a\u6b4c\u8a5e\u3001\u65cb\u5f8b\u548c\u6b4c\u8072\u7de8\u8f2f\u653e\u5728\u540c\u4e00\u689d\u6d41\u7a0b\u7684\u6846\u67b6\uff0c\u9069\u5408\u8655\u7406\u9700\u8981\u5feb\u901f\u6539\u8a5e\u3001\u6539\u65cb\u5f8b\u7684\u6b4c\u8072\u751f\u6210\u5de5\u4f5c\u3002\u514d\u624b\u5de5\u5c0d\u9f4a\u8207\u96f6\u6a23\u672c\u80fd\u529b\uff0c\u4f46 beta \u7248\u5df2\u505c\u7528\uff0c\u73fe\u6642\u8981\u6539\u7528 beta \u5206\u652f\u3002<\/p>\n","protected":false},"author":8,"featured_media":11216,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"wpai_generated_summary":"","footnotes":""},"categories":[133,76,136,128,148],"tags":[],"class_list":["post-11217","post","type-post","status-publish","format-standard","hentry","category-133","category-76","category-136","category-128","category-148"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/11217","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=11217"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/11217\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/11216"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=11217"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=11217"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=11217"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}