稳定报道时间 2026-10-02 12:00
合成语音研究对象的新审计方法
一种新的合成语音研究对象的基底被提出，包括生成来源、源规范和质量信号，从而增强对模型行为的归因能力。
01
证据
- AarXiv cs.AI一手来源2026-10-02 12:00
> Abstract: Attributing model behavior to synthetic training data requires knowing what produced each training item before estimating what that item caused.
- AarXiv cs.AI一手来源2026-10-02 12:00
Abstract: Attributing model behavior to synthetic training data requires knowing what produced each training item before estimating what that item caused. A waveform-label pair does not preserve this knowledge. We propose a generation-provenance substrate in which a synthetic research object binds source specification, generated content, waveform, target, fact requirements, quality signals, revie…
- AarXiv cs.AI一手来源2026-10-02 12:00
Comments: Accepted to the Third NeurIPS Workshop on Attributing Model Behavior at Scale: Data Attribution and Provenance. 4 pages, 0 figures, 1 table.