Comments (2)
Hello, thanks for your feedback. We have changed the early stop condition to fit the updated loss function.
BTW, the reason why we remove from the loss function the outermost maximum operation is that it will cause unexpected issue for benign voices whose initial loss is slightly larger than adver_thresh.
For example, suppose adver_thresh=0, and the initial loss of a benign voice is 0.01. This voice is not robust enough, so add a random noise is enough to make it adversarial. Hence, the samples_per_draw noisy samples are adversarial voices. If the outermost maximum operation is retained, all the loss of these noisy samples are zero. So the estimated gradient remains zero, and the sample will not be updated throughout the iteration procedure.
That 's why we can only achieve 99% ASR, and not 100% in our paper. Using the updated loss function, we can achieve 100% ASR.
from fakebob.
Thanks for sharing!
from fakebob.
Related Issues (15)
- Something wrong in 'build_spk_models.py' or 'pre-models' HOT 2
- Is gpu used in Generate adversarial voices HOT 1
- Failed building Docker: Unable to establish SSL connection HOT 7
- test.py: No such file or directory: 'model/1580.iv' HOT 8
- No such file or directory: 'ivector-plda-scoring' HOT 1
- No such file or directory: 'ivector-plda-scoring' HOT 12
- FileNotFoundError: [Errno 2] No such file or directory: 'ivector-plda-scoring' HOT 3
- ERRO[0001] error waiting for container: context canceled HOT 3
- Add enrollment error HOT 3
- The data in data.tgz/test-set/61 were wrong HOT 8
- Extracting and scoring issue at step 7 HOT 13
- Issue at step 8 test.py HOT 10
- problem in step 8 running 'test.py' about 'data' HOT 4
- test.py: No such file or directory: 'ivector-plda-scoring' HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fakebob.