
{"id":11855,"date":"2026-09-04T00:46:06","date_gmt":"2026-09-03T16:46:06","guid":{"rendered":"https:\/\/infernews.com\/blog\/vibevoice-asr-streaming\/"},"modified":"2026-09-04T00:47:04","modified_gmt":"2026-09-03T16:47:04","slug":"vibevoice-asr-streaming","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/vibevoice-asr-streaming\/","title":{"rendered":"[\u6280\u8853\u6587\u7ae0] VibeVoice-ASR-Streaming \u628a\u8b1b\u8005\u5373\u6642\u8fa8\u8b58\u8207\u8f49\u9304\u5408\u800c\u70ba\u4e00"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/09\/pasted-3b4c6267e551.jpg\" alt=\"Hugging Face\"><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">Microsoft Research\u806f\u540c\u4e2d\u570b\u79d1\u5b78\u9662\u5927\u5b78\u53ca\u4e0a\u6d77\u4ea4\u901a\u5927\u5b78\u7814\u7a76\u4eba\u54e1\uff0c\u958b\u767cVibeVoice-ASR-Streaming\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6a21\u578b\u4ee5 Large Language Model\uff08LLM\uff09\u70ba\u6838\u5fc3\u7684\u7aef\u5230\u7aef\u4e32\u6d41Speaker-Attributed Automatic Speech Recognition\uff08ASR\uff09\u7cfb\u7d71\uff0c\u9023\u7e8c\u8655\u7406\u5230\u9054\u4e2d\u7684\u8a9e\u97f3\uff0c\u540c\u6642\u8f38\u51fa\u6587\u5b57\u53ca\u8b1b\u8005\u8eab\u4efd\u3002\u50b3\u7d71\u6d41\u7a0b\u901a\u5e38\u628aASR\u8207speaker diarization\u5206\u958b\u8655\u7406\uff1b\u6b64\u6a21\u578b\u5c07\u5169\u9805\u5de5\u4f5c\u653e\u9032\u55ae\u4e00\u6a21\u578b\uff0c\u91dd\u5c0d\u5373\u6642\u8a9e\u97f3\u52a9\u624b\u53ca\u8a9e\u97f3\u4ee3\u7406\u9700\u8981\u4f4e\u5ef6\u9072\u56de\u61c9\u7684\u5834\u666f\uff0c\u6e1b\u5c11\u7b49\u5f85\u5b8c\u6574\u9304\u97f3\u5f8c\u624d\u5206\u6790\u7684\u9650\u5236\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">VibeVoice-ASR-Streaming \u6703\u4ea4\u932f\u8655\u7406\u56fa\u5b9a\u5927\u5c0f\u7684audio chunks\uff0c\u4e26\u52a0\u5165\u5c11\u91cflookahead\uff0c\u8b93\u6a21\u578b\u5728\u4fdd\u7559\u672a\u4f86\u8072\u97f3\u7247\u6bb5\u4f5c\u5224\u65b7\u7684\u540c\u6642\uff0c\u9010\u6b65\u7522\u751f\u8f49\u9304\u7d50\u679c\u3002\u56fa\u5b9a\u5206\u584a\u6709\u52a9\u63a7\u5236\u8655\u7406\u5ef6\u9072\uff0c\u4f46lookahead \u8207\u5206\u584a\u5927\u5c0f\u4e4b\u9593\u4ecd\u8981\u53d6\u6368\uff1a\u524d\u8005\u8d8a\u591a\uff0c\u8b1b\u8005\u5207\u63db\u53ca\u8a9e\u53e5\u5224\u65b7\u53ef\u80fd\u66f4\u7a69\u5b9a\uff0c\u56de\u61c9\u6642\u9593\u4ea6\u53ef\u80fd\u589e\u52a0\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u4ee5\u55ae\u4e00LLM-based\u7aef\u5230\u7aef\u6a21\u578b\u540c\u6b65\u8655\u7406ASR\u8207speaker attribution<\/li>\n<li>\u4f7f\u7528\u56fa\u5b9a\u5927\u5c0faudio chunks\u53ca\u5c11\u91cflookahead\u652f\u63f4\u4e32\u6d41\u8f38\u51fa<\/li>\n<li>\u91dd\u5c0d\u5373\u6642\u8a9e\u97f3\u52a9\u624b\u53caagents\u7684\u4f4e\u5ef6\u9072\u9700\u6c42\u8a2d\u8a08<\/li>\n<li>\u91cf\u5316\u6a94\u6848\u3001\u63a8\u8ad6\u6846\u67b6\u3001\u786c\u9ad4\u9700\u6c42\u53ca\u6548\u80fd\u6307\u6a19\u5c1a\u672a\u5728\u63d0\u4f9b\u5167\u5bb9\u4e2d\u4ea4\u4ee3<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/huggingface.co\/papers\/2609.02812\" rel=\"noopener noreferrer\"><strong>\u9805\u76ee\u4e3b\u9801<\/strong><\/a> \u00b7 <a href=\"https:\/\/arxiv.org\/pdf\/2609.02812\" rel=\"noopener noreferrer\"><strong>Paper<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Microsoft Research\u5718\u968a\u5c07\u8b1b\u8005\u8fa8\u8b58\u52a0\u5165\u4e32\u6d41\u8a9e\u97f3\u8f49\u9304\uff0c\u8b93\u8a9e\u97f3\u52a9\u624b\u66f4\u5feb\u77e5\u9053\u8ab0\u5728\u8aaa\u751a\u9ebc\u3002<\/p>\n","protected":false},"author":8,"featured_media":11854,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"wpai_generated_summary":"","footnotes":""},"categories":[173,116,29,42,40,122,128,199],"tags":[],"class_list":["post-11855","post","type-post","status-publish","format-standard","hentry","category-173","category-agentic","category-audio","category-discord","category-llama","category-ollama","category-128","category-dataset-"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/11855","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=11855"}],"version-history":[{"count":1,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/11855\/revisions"}],"predecessor-version":[{"id":11857,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/11855\/revisions\/11857"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/11854"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=11855"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=11855"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=11855"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}