PLACE：基于条件嵌入的双耳音频生成位置潜在适配方法

1. 12:00
   arXiv · Audio and Speech

   PLACE：通过条件化嵌入实现双耳音频生成的位置潜在适配

   PLACE 扩展了 pretrained any-to-audio 模型 AudioX，支持从文本、视频及可选音频提示生成双耳音频。该方法通过 Perception Encoder Core 特征增强视频条件，将文本与视频表示对齐以提取空间线索，并对生成潜在施加条件依赖的低秩变换。

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

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.