Files
icassp2027-experiment/literature_notes/49_modality_dropout_ddsd.md
2026-08-30 15:36:28 +08:00

14 lines
793 B
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Modality Drop-Out for Multimodal Device Directed Speech Detection Using Verbal and Non-Verbal Features
- 第一作者:Gautam Krishna;Apple
- 发表:ICASSP 2024
- 阅读深度:摘要及会议信息筛选
- 记录日期:2026-08-28
- 来源:[论文摘要](https://arxiv.org/abs/2310.15261)、[IEEE](https://ieeexplore.ieee.org/document/10446421/)
## 摘要与项目关系
研究对设备说话检测中韵律、声学/语言信息融合,以及缺失模态时的稳健性。使用固定工作点的误接受率衡量改进。
可以作为我们的 fixed-recall 误开口评测与缺失模态对照的参考,但非 verbal 不自动意味着视觉,不能将该韵律工作描述为逐人视觉接话。具体算法尚未完整复核,暂不建议照搬数值或超参数。