Skip to content
Hot eventLive

端到端历史音乐修复潜在空间方法

1 reports1 sources5 hr ago updated

Get the story

AI overview

2026-10-02,arXiv · Audio and Speech 发布论文,提出端到端管弦乐历史音乐修复基准。该方法通过合成退化链将无监督修复转为有监督问题,采用潜在流匹配模型,在侵入式、非侵入式和主观评估上均优于现有基线。研究同时发布9.3小时无版权历史古典音乐测试集、代码与音频demo。

Generated from reports · updated 4 hr ago

Timeline

Follow the coverage from different angles.

Oct 2, 2026
  1. arXiv · Audio and Speech
    端到端历史音乐修复潜在空间方法(arXiv · Audio and Speech)

    论文提出端到端管弦乐历史音乐修复基准,用合成退化链将无监督修复转为有监督问题。潜在流匹配模型在侵入式、非侵入式和主观评估上均优于现有基线,并发布9.3小时无版权历史古典音乐测试集、代码与音频demo。

Heat trend

Current heat 9·Comparable peak 10(Oct 2)·Comparable change over 24 hours –

02.557.510Oct2Oct2Oct2Oct2

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.