feed.xml

<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="4.3.3">Jekyll</generator><link href="https://hualizhou167.github.io/KunquDB/feed.xml" rel="self" type="application/atom+xml" /><link href="https://hualizhou167.github.io/KunquDB/" rel="alternate" type="text/html" /><updated>2024-04-07T15:59:18+08:00</updated><id>https://hualizhou167.github.io/KunquDB/feed.xml</id><title type="html">KunquDB</title><subtitle>KunquDB, a large-scale, well-annotated audio-visual dataset comprising 339 speakers and 128 hours of content. Originating from the Kunqu Opera Art Canon (Kunqu yishu dadian), KunquDB is meticulously structured by dialogue lines, providing explicit annotations such as character names, speaker names, gender, vocal manner classifications and accompanied by preliminary text transcriptions.</subtitle><author><name>Huali Zhou</name></author></feed>