Latent Space Refinement and Augmentation
Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation
Hello, I’m icebird你好,我是 icebird
I document what I build, questions I have not finished thinking about, and stories that occasionally wander beyond technology. I hope every visit leaves a new trace.我把實作過程、還沒想完的問題,以及偶爾偏離技術的故事整理在這裡。希望每次回來,都能看見一些新的痕跡。
This site is evolving網站持續整理中
Recent updates最近更新
Freshly organized notes from my notebook.最近從筆記本整理出來的內容。
Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation
The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance
Speech Self-Supervised Learning Using Diffusion Model Synthetic Data