This repo is used to host the configs and checkpoints used in our ICASSP2024 submission projects.
How to run
The codebase is work-in-progress.
Exp Description
For each model, there are four exp setups, as shown in the following table.
For example, exp1.1 refers to an experiment where:
- The genuine data comes from Librispeech.
- The training order is organized by attacker's training dataset's name.
- The training strategy is finetuning.
| Genuine Data | Librispeech | MLAAD | ||
|---|---|---|---|---|
| Task Order | By Dataset | Random | Random | |
| Finetune | exp1.1 | exp1.2 | exp1.4 | |
| One-Class Softmax | exp2.1 | exp2.2 | exp2.4 | |
| Replay | exp3.1 | exp3.2 | exp3.4 | |
| LwF | exp4.1 | exp4.2 | exp4.4 | |
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.