Hot eventLive
DeMaR:掩码替换扩散用于零样本文本转语音
1 reports1 sources4 hr ago updated
Get the story
AI overview
2026年10月8日,arXiv(Audio and Speech,一手)发表论文,提出 DeMaR 方法,将掩码替换训练与置信度排序的纯掩码采样结合,在保持总训练损坏概率不变的前提下,于 LibriTTS 上从零训练,并在相同语音 tokenizer 下取得比自回归与纯掩码扩散基线更低的词错误率(WER)。该研究聚焦零样本文本转语音中的掩码替换扩散机制探究,目前未见后续报道或矛盾信息。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
Oct 8, 2026
- arXiv · Audio and Speech零样本文本转语音中掩码替换扩散机制的探究
论文提出 DeMaR,将掩码替换训练与置信度排序的纯掩码采样结合,在保持总训练损坏概率不变的前提下,于 LibriTTS 上从零训练,在相同语音 tokenizer 下取得比自回归与纯掩码扩散基线更低的词错误率(WER)。
Heat trend
Current heat 9·Comparable peak 10(Oct 8)·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.